demand analysis research paper

• Survey Paper
• Open access
• Published: 25 July 2020

Predictive big data analytics for supply chain demand forecasting: methods, applications, and research opportunities

• Mahya Seyedan 1 &
• Fereshteh Mafakheri   ORCID: orcid.org/0000-0002-7991-4635 1  

Journal of Big Data volume  7 , Article number:  53 ( 2020 ) Cite this article

112k Accesses

123 Citations

23 Altmetric

Metrics details

Big data analytics (BDA) in supply chain management (SCM) is receiving a growing attention. This is due to the fact that BDA has a wide range of applications in SCM, including customer behavior analysis, trend analysis, and demand prediction. In this survey, we investigate the predictive BDA applications in supply chain demand forecasting to propose a classification of these applications, identify the gaps, and provide insights for future research. We classify these algorithms and their applications in supply chain management into time-series forecasting, clustering, K-nearest-neighbors, neural networks, regression analysis, support vector machines, and support vector regression. This survey also points to the fact that the literature is particularly lacking on the applications of BDA for demand forecasting in the case of closed-loop supply chains (CLSCs) and accordingly highlights avenues for future research.

Introduction

Nowadays, businesses adopt ever-increasing precision marketing efforts to remain competitive and to maintain or grow their margin of profit. As such, forecasting models have been widely applied in precision marketing to understand and fulfill customer needs and expectations [ 1 ]. In doing so, there is a growing attention to analysis of consumption behavior and preferences using forecasts obtained from customer data and transaction records in order to manage products supply chains (SC) accordingly [ 2 , 3 ].

Supply chain management (SCM) focuses on flow of goods, services, and information from points of origin to customers through a chain of entities and activities that are connected to one another [ 4 ]. In typical SCM problems, it is assumed that capacity, demand, and cost are known parameters [ 5 ]. However, this is not the case in reality, as there are uncertainties arising from variations in customers’ demand, supplies transportation, organizational risks and lead times. Demand uncertainties, in particular, has the greatest influence on SC performance with widespread effects on production scheduling, inventory planning, and transportation [ 6 ]. In this sense, demand forecasting is a key approach in addressing uncertainties in supply chains [ 7 , 8 , 9 ].

A variety of statistical analysis techniques have been used for demand forecasting in SCM including time-series analysis and regression analysis [ 10 ]. With the advancements in information technologies and improved computational efficiencies, big data analytics (BDA) has emerged as a means of arriving at more precise predictions that better reflect customer needs, facilitate assessment of SC performance, improve the efficiency of SC, reduce reaction time, and support SC risk assessment [ 11 ].

The focus of this meta-research (literature review) paper is on “demand forecasting” in supply chains. The characteristics of demand data in today’s ever expanding and sporadic global supply chains makes the adoption of big data analytics (and machine learning) approaches a necessity for demand forecasting. The digitization of supply chains [ 12 ] and incoporporation Blockchain technologies [ 13 ] for better tracking of supply chains further highlights the role of big data analytics. Supply chain data is high dimensional generated across many points in the chain for varied purposes (products, supplier capacities, orders, shipments, customers, retailers, etc.) in high volumes due to plurality of suppliers, products, and customers and in high velocity reflected by many transactions continuously processed across supply chain networks. In the sense of such complexities, there has been a departure from conventional (statistical) demand forecasting approaches that work based on identifying statistically meannignful trends (characterized by mean and variance attributes) across historical data [ 14 ], towards intelligent forecasts that can learn from the historical data and intelligently evolve to adjust to predict the ever changing demand in supply chains [ 15 ]. This capability is established using big data analytics techniques that extract forecasting rules through discovering the underlying relationships among demand data across supply chain networks [ 16 ]. These techniques are computationally intensive to process and require complex machine-programmed algorithms [ 17 ].

With SCM efforts aiming at satisfying customer demand while minimizing the total cost of supply, applying machine-learning/data analytics algorithms could facilitate precise (data-driven) demand forecasts and align supply chain activities with these predictions to improve efficiency and satisfaction. Reflecting on these opportunities, in this paper, first a taxonmy of data sources in SCM is proposed. Then, the importance of demand management in SCs is investigated. A meta-research (literature review) on BDA applications in SC demand forecasting is explored according to categories of the algorithms utilized. This review paves the path to a critical discussion of BDA applications in SCM highlighting a number of key findings and summarizing the existing challenges and gaps in BDA applications for demand forecasting in SCs. On that basis, the paper concludes by presenting a number of avenues for future research.

Data in supply chains

Data in the context of supply chains can be categorized into customer, shipping, delivery, order, sale, store, and product data [ 18 ]. Figure  1 provides the taxonomy of supply chain data. As such, SC data originates from different (and segmented) sources such as sales, inventory, manufacturing, warehousing, and transportation. In this sense, competition, price volatilities, technological development, and varying customer commitments could lead to underestimation or overestimation of demand in established forecasts [ 19 ]. Therefore, to increase the precision of demand forecast, supply chain data shall be carefully analyzed to enhance knowledge about market trends, customer behavior, suppliers and technologies. Extracting trends and patterns from such data and using them to improve accuracy of future predictions can help minimize supply chain costs [ 20 , 21 ].

Taxonomy of supply chain data

Analysis of supply chain data has become a complex task due to (1) increasing multiplicity of SC entities, (2) growing diversity of SC configurations depending on the homogeneity or heterogeneity of products, (3) interdependencies among these entities (4) uncertainties in dynamical behavior of these components, (5) lack of information as relate to SC entities; [ 11 ], (6) networked manufacturing/production entities due to their increasing coordination and cooperation to achieve a high level customization and adaptaion to varying customers’ needs [ 22 ], and finally (7) the increasing adoption of supply chain digitization practices (and use of Blockchain technologies) to track the acitivities across supply chains [ 12 , 13 ].

Big data analytics (BDA) has been increasingly applied in management of SCs [ 23 ], for procurement management (e.g., supplier selection [ 24 ], sourcing cost improvement [ 25 ], sourcing risk management [ 26 ], product research and development [ 27 ], production planning and control [ 28 ], quality management [ 29 ], maintenance, and diagnosis [ 30 ], warehousing [ 31 ], order picking [ 32 ], inventory control [ 33 ], logistics/transportation (e.g., intelligent transportation systems [ 34 ], logistics planning [ 35 ], in-transit inventory management [ 36 ], demand management (e.g., demand forecasting [ 37 ], demand sensing [ 38 ], and demand shaping [ 39 ]. A key application of BDA in SCM is to provide accurate forecasting, especially demand forecasting, with the aim of reducing the bullwhip effect [ 14 , 40 , 41 , 42 ].

Big data is defined as high-volume, high-velocity, high-variety, high value, and high veracity data requiring innovative forms of information processing that enable enhanced insights, decision making, and process automation [ 43 ]. Volume refers to the extensive size of data collected from multiple sources (spatial dimension) and over an extended period of time (temporal dimension) in SCs. For example, in case of freight data, we have ERP/WMS order and item-level data, tracking, and freight invoice data. These data are generated from sensors, bar codes, Enterprise resource planning (ERP), and database technologies. Velocity can be defined as the rate of generation and delivery of specific data; in other words, it refers to the speed of data collection, reliability of data transferring, efficiency of data storage, and excavation speed of discovering useful knowledge as relate to decision-making models and algorithms. Variety refers to generating varied types of data from diverse sources such as the Internet of Things (IoT), mobile devices, online social networks, and so on. For instance, the vast data from SCM are usually variable due to the diverse sources and heterogeneous formats, particularly resulted from using various sensors in manufacturing sites, highways, retailer shops, and facilitated warehouses. Value refers to the nature of the data that must be discovered to support decision-making. It is the most important yet the most elusive, of the 5 Vs. Veracity refers to the quality of data, which must be accurate and trustworthy, with the knowledge that uncertainty and unreliability may exist in many data sources. Veracity deals with conformity and accuracy of data. Data should be integrated from disparate sources and formats, filtered and validated [ 23 , 44 , 45 ]. In summary, big data analytics techniques can deal with a collection of large and complex datasets that are difficult to process and analyze using traditional techniques [ 46 ].

The literature points to multiple sources of big data across the supply chains with varied trade-offs among volume, velocity, variety, value, and veracity attributes [ 47 ]. We have summarized these sources and trade-offs in Table  1 . Although, the demand forecasts in supply chains belong to the lower bounds of volume, velocity, and variety, however, these forecasts can use data from all sources across the supply chains from low volume/variety/velocity on-the-shelf inventory reports to high volume/variety/velocity supply chain tracking information provided through IoT. This combination of data sources used in SC demand forecasts, with their diverse temporal and spatial attributes, places a greater emphasis on use of big data analytics in supply chains, in general, and demand forecasting efforts, in particular.

The big data analytics applications in supply chain demand forecasting have been reported in both categories of supervised and unsupervised learning. In supervised learning, data will be associated with labels, meaning that the inputs and outputs are known. The supervised learning algorithms identify the underlying relationships between the inputs and outputs in an effort to map the inputs to corresponding outputs given a new unlabeled dataset [ 48 ]. For example, in case of a supervised learning model for demand forecasting, future demand can be predicted based on the historical data on product demand [ 41 ]. In unsupervised learning, data are unlabeled (i.e. unknown output), and the BDA algorithms try to find the underlying patterns among unlabeled data [ 48 ] by analyzing the inputs and their interrelationships. Customer segmentation is an example of unsupervised learning in supply chains that clusters different groups of customers based on their similarity [ 49 ]. Many machine-learning/data analytics algorithms can facilitate both supervised learning (extracting the input–output relationships) and unsupervised learning (extracting inputs, outputs and their relationships) [ 41 ].

Demand management in supply chains

The term “demand management” emerged in practice in the late 1980s and early 1990s. Traditionally, there are two approaches for demand management. A forward approach which looks at potential demand over the next several years and a backward approach that relies on past or ongoing capabilities in responding to demand [ 50 ].

In forward demand management, the focus will be on demand forecasting and planning, data management, and marketing strategies. Demand forecasting and planning refer to predicting the quantities and timings of customers’ requests. Such predictions aim at achieving customers’ satisfaction by meeting their needs in a timely manner [ 51 ]. Accurate demand forecasting could improve the efficiency and robustness of production processes (and the associated supply chains) as the resources will be aligned with requirements leading to reduction of inventories and wastes [ 52 , 53 ].

In the light of the above facts, there are many approaches proposed in the literature and practice for demand forecasting and planning. Spreadsheet models, statistical methods (like moving averages), and benchmark-based judgments are among these approaches. Today, the most widely used demand forecasting and planning tool is Excel. The most widespread problem with spreadsheet models used for demand forecasting is that they are not scalable for large-scale data. In addition, the complexities and uncertainties in SCM (with multiplicity and variability of demand and supply) cannot be extracted, analyzed, and addressed through simple statistical methods such as moving averages or exponential smoothing [ 50 ]. During the past decade, traditional solutions for SC demand forecasting and planning have faced many difficulties in driving the costs down and reducing inventories [ 50 ]. Although, in some cases, the suggested solutions have improved the day’s payable, they have pushed up the SC costs as a burden to suppliers.

The era of big data and high computing analytics has enabled data processing at a large scale that is efficient, fast, easy, and with reduced concerns about data storage and collection due to cloud services. The emergence of new technologies in data storage and analytics and the abundance of quality data have created new opportunities for data-driven demand forecasting and planning. Demand forecast accuracy can be significantly improved with data-mining algorithms and tools that can sift through data, analyze the results, and learn about the relationships involved. This could lead to highly accurate demand forecasting models that learn from data and are scalable for application in SCM. In the following section, a review of BDA applications in SCM is presented. These applications are categorized based on the employed techniques in establishing the data-drive demand forecasts.

BDA for demand forecasting in SCM

This survey aims at reviewing the articles published in the area of demand and sales forecasting in SC in the presence of big data to provide a classification of the literature based on algorithms utilized as well as a survey of applications. To the best of our knowledge, no comprehensive review of the literature specifically on SC demand forecasting has been conducted with a focus on classification of techniques of data analytics and machine learning. In doing so, we performed a thorough search of the existing literature, through Scopus, Google Scholar, and Elsevier, with publication dates ranging from 2005 to 2019. The keywords used for the search were supply chain, demand forecasting, sales forecasting, big data analytics, and machine learning.

Figure  2 shows the trend analysis of publications in demand forecasting for SC appeared from 2005 to 2019. There is a steadily increasing trend in the number of publications from 2005 to 2019. It is expected that such growth continues in 2020. Reviewing the past 15 years of research on big data analysis/machine learning applications in SC demand forecasting, we identified 64 research papers (excluding books, book chapters, and review papers) and categorized them with respect to the methodologies adopted for demand forecasting. The five most frequently used techniques are listed in Table  2 that includes “Neural Network,” “Regression”, “Time-series forecasting (ARIMA)”, “Support Vector Machine”, and “Decision Tree” methods. This table implies the growing use of big data analysis techniques in SC demand forecasting. It shall be mentioned that there were a few articles using multiple of these techniques.

Distribution of literature in supply chain demand forecasting from 2005 to 2019

It shall be mentioned that there are literature review papers exploring the use of big data analytics in SCM [ 10 , 16 , 23 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 ]. However, this study focuses on the specific topic of “demand forecasting” in SCM to explore BDA applications in line with this particular subtopic in SCM.

As Hofmann and Rutschmann [ 58 ] indicated in their literature review, the key questions to answer are why, what and how big data analytics/machine-learning algorithms could enhance forecasts’ accuracy in comparison to conventional statistical forecasting approaches.

Conventional methods have faced a number of limitations for demand forecasting in the context of SCs. There are a lot of parameters influencing the demand in supply chains, however, many of them were not captured in studies using conventional methods for the sake of simplicity. In this regard, the forecasts could only provide a partial understanding of demand variations in supply chains. In addition, the unexplained demand variations could be simply considered as statistical noise. Conventional approaches could provide shorter processing times in exchange for a compromise on robustness and accuracy of predictions. Conventional SC demand forecasting approaches are mostly done manually with high reliance on the planner’s skills and domain knowledge. It would be worthwhile to fully automate the forecasting process to reduce such a dependency [ 58 ]. Finally, data-driven techniques could learn to incorporate non-linear behaviors and could thus provide better approximations in demand forecasting compared to conventional methods that are mostly derived based on linear models. There is a significant level of non-linearity in demand behavior in SC particularly due to competition among suppliers, the bullwhip effect, and mismatch between supply and demand [ 40 ].

To extract valuable knowledge from a vast amount of data, BDA is used as an advanced analytics technique to obtain the data needed for decision-making. Reduced operational costs, improved SC agility, and increased customer satisfaction are mentioned among the benefits of applying BDA in SCM [ 68 ]. Researchers used various BDA techniques and algorithms in SCM context, such as classification, scenario analysis, and optimization [ 23 ]. Machine-learning techniques have been used to forecast demand in SCs, subject to uncertainties in prices, markets, competitors, and customer behaviors, in order to manage SCs in a more efficient and profitable manner [ 40 ].

BDA has been applied in all stages of supply chains, including procurement, warehousing, logistics/transportation, manufacturing, and sales management. BDA consists of descriptive analytics, predictive analytics, and prescriptive analytics. Descriptive analysis is defined as describing and categorizing what happened in the past. Predictive analytics are used to predict future events and discover predictive patterns within data by using mathematical algorithms such as data mining, web mining, and text mining. Prescriptive analytics apply data and mathematical algorithms for decision-making. Multi-criteria decision-making, optimization, and simulation are among the prescriptive analytics tools that help to improve the accuracy of forecasting [ 10 ].

Predictive analytics are the ones mostly utilized in SC demand and procurement forecasting [ 23 ]. In this sense, in the following subsections, we will review various predictive big data analytics approaches, presented in the literature for demand forecasting in SCM, categorized based on the employed data analytics/machine learning technique/algorithm, with elaborations of their purpose and applications (summarized in Table  3 ).

Time-series forecasting

Time series are methodologies for mining complex and sequential data types. In time-series data, sequence data, consisting of long sequences of numeric data, recorded at equal time intervals (e.g., per minute, per hour, or per day). Many natural and human-made processes, such as stock markets, medical diagnosis, or natural phenomenon, can generate time-series data. [ 48 ].

In case of demand forecasting using time-series, demand is recorded over time at equal size intervals [ 69 , 70 ]. Combinations of time-series methods with product or market features have attracted much attention in demand forecasting with BDA. Ma et al. [ 71 ] proposed and developed a demand trend-mining algorithm for predictive life cycle design. In their method, they combined three models (a) a decision tree model for large-scale historical data classification, (b) a discrete choice analysis for present and past demand modeling, and (c) an automated time-series forecasting model for future trend analysis. They tested and applied their 3-level approach in smartphone design, manufacturing and remanufacturing.

Time-series approach was used for forecasting of search traffic (service demand) subject to changes in consumer attitudes [ 37 ]. Demand forecasting has been achieved through time-series models using exponential smoothing with covariates (ESCov) to provide predictions for short-term, mid-term, and long-term demand trends in the chemical industry SCs [ 7 ]. In addition, Hamiche et al. [ 72 ] used a customer-responsive time-series approach for SC demand forecasting.

In case of perishable products, with short life cycles, having appropriate (short-term) forecasting is extremely critical. Da Veiga et al. [ 73 ] forecasted the demand for a group of perishable dairy products using Autoregressive Integrated Moving Average (ARIMA) and Holt-Winters (HW) models. The results were compared based on mean absolute percentage error (MAPE) and Theil inequality index (U-Theil). The HW model showed a better goodness-of-fit based on both performance metrics.

In case of ARIMA, the accuracy of predictions could diminish where there exists a high level of uncertainty in future patterns of parameters [ 42 , 74 , 75 , 76 ]. HW model forecasting can yield better accuracy in comparison to ARIMA [ 73 ]. HW is simple and easy to use. However, data horizon could not be larger than a seasonal cycle; otherwise, the accuracy of forecasts will decrease sharply. This is due to the fact that inputs of an HW model are themselves predicted values subject to longer-term potential inaccuracies and uncertainties [ 45 , 73 ].

Clustering analysis

Clustering analysis is a data analysis approach that partitions a group of data objects into subgroups based on their similarities. Several applications of clustering analysis has been reported in business analytics, pattern recognition, and web development [ 48 ]. Han et al. [ 48 ] have emphasized the fact that using clustering customers can be organized into groups (clusters), such that customers within a group present similar characteristic.

A key target of demand forecasting is to identify demand behavior of customers. Extraction of similar behavior from historical data leads to recognition of customer clusters or segments. Clustering algorithms such as K-means, self-organizing maps (SOMs), and fuzzy clustering have been used to segment similar customers with respect to their behavior. The clustering enhances the accuracy of SC demand forecasting as the predictions are established for each segment comprised of similar customers. As a limitation, the clustering methods have the tendency to identify the customers, that do not follow a pattern, as outliers [ 74 , 77 ].

Hierarchical forecasts of sales data are performed by clustering and categorization of sales patterns. Multivariate ARIMA models have been used in demand forecasting based on point-of-sales data in industrial bakery chains [ 19 ]. These bakery goods are ordered and clustered daily with a continuous need to demand forecasts in order to avoid both shortage or waste [ 19 ]. Fuel demand forecasting in thermal power plants is another domain with applications of clustering methods. Electricity consumption patterns are derived using a clustering of consumers, and on that basis, demand for the required fuel is established [ 77 ].

K-nearest-neighbor (KNN)

KNN is a method of classification that has been widely used for pattern recognition. KNN algorithm identifies the similarity of a given object to the surrounding objects (called tuples) by generating a similarity index. These tuples are described by n attributes. Thus, each tuple corresponds to a point in an n-dimensional space. The KNN algorithm searches for k tuples that are closest to a given tuple [ 48 ]. These similarity-based classifications will lead to formation of clusters containing similar objects. KNN can also be integrated into regression analysis problems [ 78 ] for dimensionality reduction of the data [ 79 ]. In the realm of demand forecasting in SC, Nikolopoulos et al. [ 80 ] applied KNN for forecasting sporadic demand in an automotive spare parts supply chain. In another study, KNN is used to forecast future trends of demand for Walmart’s supply chain planning [ 81 ].

Artificial neural networks

In artificial neural networks, a set of neurons (input/output units) are connected to one another in different layers in order to establish mapping of the inputs to outputs by finding the underlying correlations between them. The configuration of such networks could become a complex problem, due to a high number of layers and neurons, as well as variability of their types (linear or nonlinear), which needs to follow a data-driven learning process to be established. In doing so, each unit (neuron) will correspond to a weight, that is tuned through a training step [ 48 ]. At the end, a weighted network with minimum number of neurons, that could map the inputs to outputs with a minimum fitting error (deviation), is identified.

As the literature reveals, artificial neural networks (ANN) are widely applied for demand forecasting [ 82 , 83 , 84 , 85 ]. To improve the accuracy of ANN-based demand predictions, Liu et al. [ 86 ] proposed a combination of a grey model and a stacked auto encoder applied to a case study of predicting demand in a Brazilian logistics company subject to transportation disruption [ 87 ]. Amirkolaii et al. [ 88 ] applied neural networks in forecasting spare parts demand to minimize supply chain shortages. In this case of spare parts supply chain, although there were multiple suppliers to satisfy demand for a variety of spare parts, the demand was subject to high variability due to a varying number of customers and their varying needs. Their proposed ANN-based forecasting approach included (1) 1 input demand feature with 1 Stock-Keeping Unit (SKU), (2) 1 input demand feature with all SKUs, (3) 16 input demand features with 1 SKU, and (4) 16 input demand features with all SKUs. They applied neural networks with back propagation and compared the results with a number of benchmarks reporting a Mean Square Error (MSE) for each configuration scenario.

Huang et al. [ 89 ] compared a backpropagation (BP) neural network and a linear regression analysis for forecasting of e-logistics demand in urban and rural areas in China using data from 1997 to 2015. By comparing mean absolute error (MAE) and the average relative errors of backpropagation neural network and linear regression, they showed that backpropagation neural networks could reach higher accuracy (reflecting lower differences between predicted and actual data). This is due to the fact that a Sigmoid function was used as the transfer function in the hidden layer of BP, which is differentiable for nonlinear problems such as the one presented in their case study, whereas the linear regression works well with linear problems.

ANNs have also been applied in demand forecasting for server models with one-week demand prediction ahead of order arrivals. In this regard, Saha et al. [ 90 ] proposed an ANN-based forecasting model using a 52-week time-series data fitted through both BP and Radial Basis Function (RBF) networks. A RBF network is similar to a BP network except for the activation/transfer function in RBF that follows a feed-forward process using a radial basis function. RBF results in faster training and convergence to ANN weights in comparison with BP networks without compromising the forecasting precision.

Researchers have combined ANN-based machine-learning algorithms with optimization models to draw optimal courses of actions, strategies, or decisions for future. Chang et al. [ 91 ] employed a genetic algorithm in the training phase of a neural network using sales/supply chain data in the printed circuit board industry in Taiwan and presented an evolving neural network-forecasting model. They proposed use of a Genetic Algorithms (GA)-based cost function optimization to arrive at the best configuration of the corresponding neural network for sales forecast with respect to prediction precision. The proposed model was then compared to back-propagation and linear regression approaches using three performance indices of MAPE, Mean Absolute Deviation (MAD), and Total Cost Deviation (TCD), presenting its superior prediction precision.

Regression analysis

Regression models are used to generate continuous-valued functions utilized for prediction. These methods are used to predict the value of a response (dependent) variable with respect to one or more predictor (independent) variables. There are various forms of regression analysis, such as linear, multiple, weighted, symbolic (random), polynomial, nonparametric, and robust. The latter approach is useful when errors fail to satisfy normalcy conditions or when we deal with big data that could contain significant number of outliers [ 48 ].

Merkuryeva et al. [ 92 ] analyzed three prediction approaches for demand forecasting in the pharmaceutical industry: a simple moving average model, multiple linear regressions, and a symbolic regression with searches conducted through an evolutionary genetic programming. In this experiment, symbolic regression exhibited the best fit with the lowest error.

As perishable products must be sold due to a very short preservation time, demand forecasting for this type of products has drawn increasing attention. Yang and Sutrisno [ 93 ] applied and compared regression analysis and neural network techniques to derive demand forecasts for perishable goods. They concluded that accurate daily forecasts are achievable with knowledge of sales numbers in the first few hours of the day using either of the above methods.

Support vector machine (SVM)

SVM is an algorithm that uses a nonlinear mapping to transform a set of training data into a higher dimension (data classes). SVM searches for an optimal separating hyper-plane that can separate the resulting class from another) [ 48 ]. Villegas et al. [ 94 ] tested the applicability of SVMs for demand forecasting in household and personal care SCs with a dataset comprised of 229 weekly demand series in the UK. Wu [ 95 ] applied an SVM, using a particle swarm optimization (PSO) to search for the best separating hyper-plane, classifying the data related to car sales and forecasting the demand in each cluster.

Support vector regression (SVR)

Continuous variable classification problems can be solved by support vector regression (SVR), which is a regression implementation of SVM. The main idea behind SVR regression is the computation of a linear regression function within a high-dimensional feature space. SVR has been applied in financial/cost prediction problems, handwritten digit recognition, and speaker identification, object recognition, etc. [ 48 ].

Guanghui [ 96 ] used the SVR method for SC needs prediction. The use of SVR in demand forecasting can yield a lower mean square error than RBF neural networks due to the fact that the optimization (cost) function in SVR does not consider the points beyond a margin of distance from the training set. Therefore, this method leads to higher forecast accuracy, although, similar to SVM, it is only applicable to a two-class problem (such as normal versus anomaly detection/estimation problems). Sarhani and El Afia [ 97 ] sought to forecast SC demand using SVR and applied Particle swarm optimization (PSO) and GA to optimize SVR parameters. SVR-PSO and SVR-GA approaches were compared with respect to accuracy of predictions using MAPE. The results showed a superior performance by PSO in terms time intensity and MAPE when configuring the SVR parameters.

Mixed approaches

Some works in the literature have used a combination of the aforementioned techniques. In these studies, the data flow into a sequence of algorithms and the outputs of one stage become inputs of the next step. The outputs are explanatory in the form of qualitative and quantitative information with a sequence of useful information extracted out of each algorithm. Examples of such studies include [ 15 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 ].

In more complex supply chains with several points of supply, different warehouses, varied customers, and several products, the demand forecasting becomes a high dimensional problem. To address this issue, Islek and Oguducu [ 100 ] applied a clustering technique, called bipartite graph clustering, to analyze the patterns of sales for different products. Then, they combined a moving average model and a Bayesian belief network approaches to improve the accuracy of demand forecasting for each cluster. Kilimci et al. [ 101 ] developed an intelligent demand forecasting system by applying time-series and regression methods, a support vector regression algorithm, and a deep learning model in a sequence. They dealt with a case involving big amount of data accounting for 155 features over 875 million records. First, they used a principal component analysis for dimension reduction. Then, data clustering was performed. This is followed by demand forecasting for each cluster using a novel decision integration strategy called boosting ensemble. They concluded that the combination of a deep neural network with a boosting strategy yielded the best accuracy, minimizing the prediction error for demand forecasting.

Chen and Lu [ 98 ] combined clustering algorithms of SOM, a growing hierarchical self-organizing mapping (GHSOM), and K-means, with two machine-learning techniques of SVR and extreme learning machine (ELM) in sales forecasting of computers. The authors found that the combination of GHSOM and ELM yielded better accuracy and performance in demand forecasts for their computer retailing case study. Difficulties in forecasting also occur in cases with high product variety. For these types of products in an SC, patterns of sales can be extracted for clustered products. Then, for each cluster, a machine-learning technique, such as SVR, can be employed to further improve the prediction accuracy [ 104 ].

Brentan et al. [ 106 ] used and analyzed various BDA techniques for demand prediction; including support vector machines (SVM), and adaptive neural fuzzy inference systems (ANFIS). They combined the predicted values derived from each machine learning techniques, using a linear regression process to arrive at an average prediction value adopted as the benchmark forecast. The performance (accuracy) of each technique is then analyzed with respect to their mean square root error (RMSE) and MAE values obtained through comparing the target values and the predicted ones.

In summary, Table  3 provides an overview of the recent literature on the application of Predictive BDA in demand forecasting.

Discussions

The data produced in SCs contain a great deal of useful knowledge. Analysis of such massive data can help us to forecast trends of customer behavior, markets, prices, and so on. This can help organizations better adapt to competitive environments. To forecast demand in an SC, with the presences of big data, different predictive BDA algorithms have been used. These algorithms could provide predictive analytics using time-series approaches, auto-regressive methods, and associative forecasting methods [ 10 ]. The demand forecasts from these BDA methods could be integrated with product design attributes as well as with online search traffic mapping to incorporate customer and price information [ 37 , 71 ].

Predictive BDA algorithms

Most of the studies examined, developed and used a certain data-mining algorithm for their case studies. However, there are very few comparative studies available in the literature to provide a benchmark for understanding of the advantages and disadvantages of these methodologies. Additionally, as depicted by Table  3 , there is no clear trend between the choice of the BDA algorithm/method and the application domain or category.

Predictive BDA applicability

Most data-driven models used in the literature consider historical data. Such a backward-looking forecasting ignores the new trends and highs and lows in different economic environments. Also, organizational factors, such as reputation and marketing strategies, as well as internal risks (related to availability of SCM resources), could greatly influence the demand [ 107 ] and thus contribute to inaccuracy of BDA-based demand predictions using historical data. Incorporating existing driving factors outside the historical data, such as economic instability, inflation, and purchasing power, could help adjust the predictions with respect to unseen future scenarios of demand. Combining predictive algorithms with optimization or simulation can equip the models with prescriptive capabilities in response to future scenarios and expectations.

Predictive BDA in closed-loop supply chains (CLSC)

The combination of forward and reverse flow of material in a SC is referred to as a closed-loop supply chain (CLSC). A CLSC is a more complex system than a traditional SC because it consists of the forward and reverse SC simultaneously [ 108 ]. Economic impact, environmental impact, and social responsibility are three significant factors in designing a CLSC network with inclusion of product recycling, remanufacturing, and refurbishment functions. The complexity of a CLSC, compared to a common SC, results from the coordination between backward and forward flows. For example, transportation cost, holding cost, and forecasting demand are challenging issues because of uncertainties in the information flows from the forward chain to the reverse one. In addition, the uncertainties about the rate of returned products and efficiencies of recycling, remanufacturing, and refurbishment functions are some of the main barriers in establishing predictions for the reverse flow [ 5 , 6 , 109 ]. As such, one key finding from this literature survey is that CLSCs particularly deal with the lack of quality data for remanufacturing. Remanufacturing refers to the disassembly of products, cleaning, inspection, storage, reconditioning, replacement, and reassembling. As a result of deficiencies in data, optimal scheduling of remanufacturing functions is cumbersome due to uncertainties in the quality and quantity of used products as well as timing of returns and delivery delays.

IoT-based approaches can overcome the difficulties of collecting data in a CLSC. In an IoT environment, objects are monitored and controlled remotely across existing network infrastructures. This enables more direct integration between the physical world and computer-based systems. The results include improved efficiency, accuracy, and economic benefit across SCs [ 50 , 54 , 110 ].

Radio frequency identification (RFID) is another technology that has become very popular in SCs. RFID can be used for automation of processes in an SC, and it is useful for coordination of forecasts in CLSCs with dispersed points of return and varied quantities and qualities of returned used products [ 10 , 111 , 112 , 113 , 114 ].

Conclusions

The growing need to customer behavior analysis and demand forecasting is deriven by globalization and increasing market competitions as well as the surge in supply chain digitization practices. In this study, we performed a thorough review for applications of predictive big data analytics (BDA) in SC demand forecasting. The survey overviewed the BDA methods applied to supply chain demand forecasting and provided a comparative categorization of them. We collected and analyzed these studies with respect to methods and techniques used in demand prediction. Seven mainstream techniques were identified and studied with their pros and cons. The neural networks and regression analysis are observed as the two mostly employed techniques, among others. The review also pointed to the fact that optimization models or simulation can be used to improve the accuracy of forecasting through formulating and optimizing a cost function for the fitting of the predictions to data.

One key finding from reviewing the existing literature was that there is a very limited research conducted on the applications of BDA in CLSC and reverse logistics. There are key benefits in adopting a data-driven approach for design and management of CLSCs. Due to increasing environmental awareness and incentives from the government, nowadays a vast quantity of returned (used) products are collected, which are of various types and conditions, received and sorted in many collection points. These uncertainties have a direct impact on the cost-efficiency of remanufacturing processes, the final price of the refurbished products and the demand for these products [ 115 ]. As such, design and operation of CLSCs present a case for big data analytics from both supply and demand forecasting perspectives.

Availability of data and materials

The paper presents a review of the literature extracted from main scientific databases without presenting data.

Abbreviations

Adaptive neural fuzzy inference systems

Auto regressive integrated moving average

Artificial neural network

• Big data analytics

Backpropagation

Closed-loop supply chain

Extreme learning machine

Enterprise resource planning

Genetic algorithms

Growing hierarchical self-organizing map

Holt-winters

Internet of things

K-nearest-neighbor

Mean absolute deviation

Mean absolute error

Mean absolute percentage error

Mean square error

Mean square root error

Radial basis function

Particle swarm optimization

Self-organizing maps

Stock-keeping unit

Supply chain analytics

Supply chain

• Supply chain management

Support vector machine

Support vector regression

Total cost deviation

Theil inequality index

You Z, Si Y-W, Zhang D, Zeng X, Leung SCH, Li T. A decision-making framework for precision marketing. Expert Syst Appl. 2015;42(7):3357–67. https://doi.org/10.1016/J.ESWA.2014.12.022 .

Article   Google Scholar  

Guo ZX, Wong WK, Li M. A multivariate intelligent decision-making model for retail sales forecasting. Decis Support Syst. 2013;55(1):247–55. https://doi.org/10.1016/J.DSS.2013.01.026 .

Wei J-T, Lee M-C, Chen H-K, Wu H-H. Customer relationship management in the hairdressing industry: an application of data mining techniques. Expert Syst Appl. 2013;40(18):7513–8. https://doi.org/10.1016/J.ESWA.2013.07.053 .

Lu LX, Swaminathan JM. Supply chain management. Int Encycl Soc Behav Sci. 2015. https://doi.org/10.1016/B978-0-08-097086-8.73032-7 .

Gholizadeh H, Tajdin A, Javadian N. A closed-loop supply chain robust optimization for disposable appliances. Neural Comput Appl. 2018. https://doi.org/10.1007/s00521-018-3847-9 .

Tosarkani BM, Amin SH. A possibilistic solution to configure a battery closed-loop supply chain: multi-objective approach. Expert Syst Appl. 2018;92:12–26. https://doi.org/10.1016/J.ESWA.2017.09.039 .

Blackburn R, Lurz K, Priese B, Göb R, Darkow IL. A predictive analytics approach for demand forecasting in the process industry. Int Trans Oper Res. 2015;22(3):407–28. https://doi.org/10.1111/itor.12122 .

Article   MathSciNet   MATH   Google Scholar  

Boulaksil Y. Safety stock placement in supply chains with demand forecast updates. Oper Res Perspect. 2016;3:27–31. https://doi.org/10.1016/J.ORP.2016.07.001 .

Article   MathSciNet   Google Scholar  

Tang CS. Perspectives in supply chain risk management. Int J Prod Econ. 2006;103(2):451–88. https://doi.org/10.1016/J.IJPE.2005.12.006 .

Wang G, Gunasekaran A, Ngai EWT, Papadopoulos T. Big data analytics in logistics and supply chain management: certain investigations for research and applications. Int J Prod Econ. 2016;176:98–110. https://doi.org/10.1016/J.IJPE.2016.03.014 .

Awwad M, Kulkarni P, Bapna R, Marathe A. Big data analytics in supply chain: a literature review. In: Proceedings of the international conference on industrial engineering and operations management, 2018(SEP); 2018, p. 418–25.

Büyüközkan G, Göçer F. Digital Supply Chain: literature review and a proposed framework for future research. Comput Ind. 2018;97:157–77.

Kshetri N. 1 Blockchain’s roles in meeting key supply chain management objectives. Int J Inf Manage. 2018;39:80–9.

Michna Z, Disney SM, Nielsen P. The impact of stochastic lead times on the bullwhip effect under correlated demand and moving average forecasts. Omega. 2019. https://doi.org/10.1016/J.OMEGA.2019.02.002 .

Zhu Y, Zhao Y, Zhang J, Geng N, Huang D. Spring onion seed demand forecasting using a hybrid Holt-Winters and support vector machine model. PLoS ONE. 2019;14(7):e0219889. https://doi.org/10.1371/journal.pone.0219889 .

Govindan K, Cheng TCE, Mishra N, Shukla N. Big data analytics and application for logistics and supply chain management. Transport Res Part E Logist Transport Rev. 2018;114:343–9. https://doi.org/10.1016/J.TRE.2018.03.011 .

Bohanec M, Kljajić Borštnar M, Robnik-Šikonja M. Explaining machine learning models in sales predictions. Expert Syst Appl. 2017;71:416–28. https://doi.org/10.1016/J.ESWA.2016.11.010 .

Constante F, Silva F, Pereira A. DataCo smart supply chain for big data analysis. Mendeley Data. 2019. https://doi.org/10.17632/8gx2fvg2k6.5 .

Huber J, Gossmann A, Stuckenschmidt H. Cluster-based hierarchical demand forecasting for perishable goods. Expert Syst Appl. 2017;76:140–51. https://doi.org/10.1016/J.ESWA.2017.01.022 .

Ali MM, Babai MZ, Boylan JE, Syntetos AA. Supply chain forecasting when information is not shared. Eur J Oper Res. 2017;260(3):984–94. https://doi.org/10.1016/J.EJOR.2016.11.046 .

Bian W, Shang J, Zhang J. Two-way information sharing under supply chain competition. Int J Prod Econ. 2016;178:82–94. https://doi.org/10.1016/J.IJPE.2016.04.025 .

Mourtzis D. Challenges and future perspectives for the life cycle of manufacturing networks in the mass customisation era. Logist Res. 2016;9(1):2.

Nguyen T, Zhou L, Spiegler V, Ieromonachou P, Lin Y. Big data analytics in supply chain management: a state-of-the-art literature review. Comput Oper Res. 2018;98:254–64. https://doi.org/10.1016/J.COR.2017.07.004 .

Choi Y, Lee H, Irani Z. Big data-driven fuzzy cognitive map for prioritising IT service procurement in the public sector. Ann Oper Res. 2018;270(1–2):75–104. https://doi.org/10.1007/s10479-016-2281-6 .

Huang YY, Handfield RB. Measuring the benefits of erp on supply management maturity model: a “big data” method. Int J Oper Prod Manage. 2015;35(1):2–25. https://doi.org/10.1108/IJOPM-07-2013-0341 .

Miroslav M, Miloš M, Velimir Š, Božo D, Đorđe L. Semantic technologies on the mission: preventing corruption in public procurement. Comput Ind. 2014;65(5):878–90. https://doi.org/10.1016/J.COMPIND.2014.02.003 .

Zhang Y, Ren S, Liu Y, Si S. A big data analytics architecture for cleaner manufacturing and maintenance processes of complex products. J Clean Prod. 2017;142:626–41. https://doi.org/10.1016/J.JCLEPRO.2016.07.123 .

Shu Y, Ming L, Cheng F, Zhang Z, Zhao J. Abnormal situation management: challenges and opportunities in the big data era. Comput Chem Eng. 2016;91:104–13. https://doi.org/10.1016/J.COMPCHEMENG.2016.04.011 .

Krumeich J, Werth D, Loos P. Prescriptive control of business processes: new potentials through predictive analytics of big data in the process manufacturing industry. Bus Inform Syst Eng. 2016;58(4):261–80. https://doi.org/10.1007/s12599-015-0412-2 .

Guo SY, Ding LY, Luo HB, Jiang XY. A Big-Data-based platform of workers’ behavior: observations from the field. Accid Anal Prev. 2016;93:299–309. https://doi.org/10.1016/J.AAP.2015.09.024 .

Chuang Y-F, Chia S-H, Wong J-Y. Enhancing order-picking efficiency through data mining and assignment approaches. WSEAS Transactions on Business and Economics. 2014;11(1):52–64.

Google Scholar  

Ballestín F, Pérez Á, Lino P, Quintanilla S, Valls V. Static and dynamic policies with RFID for the scheduling of retrieval and storage warehouse operations. Comput Ind Eng. 2013;66(4):696–709. https://doi.org/10.1016/J.CIE.2013.09.020 .

Alyahya S, Wang Q, Bennett N. Application and integration of an RFID-enabled warehousing management system—a feasibility study. J Ind Inform Integr. 2016;4:15–25. https://doi.org/10.1016/J.JII.2016.08.001 .

Cui J, Liu F, Hu J, Janssens D, Wets G, Cools M. Identifying mismatch between urban travel demand and transport network services using GPS data: a case study in the fast growing Chinese city of Harbin. Neurocomputing. 2016;181:4–18. https://doi.org/10.1016/J.NEUCOM.2015.08.100 .

Shan Z, Zhu Q. Camera location for real-time traffic state estimation in urban road network using big GPS data. Neurocomputing. 2015;169:134–43. https://doi.org/10.1016/J.NEUCOM.2014.11.093 .

Ting SL, Tse YK, Ho GTS, Chung SH, Pang G. Mining logistics data to assure the quality in a sustainable food supply chain: a case in the red wine industry. Int J Prod Econ. 2014;152:200–9. https://doi.org/10.1016/J.IJPE.2013.12.010 .

Jun S-P, Park D-H, Yeom J. The possibility of using search traffic information to explore consumer product attitudes and forecast consumer preference. Technol Forecast Soc Chang. 2014;86:237–53. https://doi.org/10.1016/J.TECHFORE.2013.10.021 .

He W, Wu H, Yan G, Akula V, Shen J. A novel social media competitive analytics framework with sentiment benchmarks. Inform Manage. 2015;52(7):801–12. https://doi.org/10.1016/J.IM.2015.04.006 .

Marine-Roig E, Anton Clavé S. Tourism analytics with massive user-generated content: a case study of Barcelona. J Destination Market Manage. 2015;4(3):162–72. https://doi.org/10.1016/J.JDMM.2015.06.004 .

Carbonneau R, Laframboise K, Vahidov R. Application of machine learning techniques for supply chain demand forecasting. Eur J Oper Res. 2008;184(3):1140–54. https://doi.org/10.1016/J.EJOR.2006.12.004 .

Article   MATH   Google Scholar  

Munir K. Cloud computing and big data: technologies, applications and security, vol. 49. Berlin: Springer; 2019.

Rostami-Tabar B, Babai MZ, Ali M, Boylan JE. The impact of temporal aggregation on supply chains with ARMA(1,1) demand processes. Eur J Oper Res. 2019;273(3):920–32. https://doi.org/10.1016/J.EJOR.2018.09.010 .

Beyer MA, Laney D. The importance of ‘big data’: a definition. Stamford: Gartner; 2012. p. 2014–8.

Benabdellah AC, Benghabrit A, Bouhaddou I, Zemmouri EM. Big data for supply chain management: opportunities and challenges. In: Proceedings of IEEE/ACS international conference on computer systems and applications, AICCSA, no. 11, p. 20–26; 2016. https://doi.org/10.1109/AICCSA.2016.7945828 .

Kumar M. Applied big data analytics in operations management. Appl Big Data Anal Oper Manage. 2016. https://doi.org/10.4018/978-1-5225-0886-1 .

Zhong RY, Huang GQ, Lan S, Dai QY, Chen X, Zhang T. A big data approach for logistics trajectory discovery from RFID-enabled production data. Int J Prod Econ. 2015;165:260–72. https://doi.org/10.1016/J.IJPE.2015.02.014 .

Varela IR, Tjahjono B. Big data analytics in supply chain management: trends and related research. In: 6th international conference on operations and supply chain management, vol. 1, no. 1, p. 2013–4; 2014. https://doi.org/10.13140/RG.2.1.4935.2563 .

Han J, Kamber M, Pei J. Data mining: concepts and techniques. Burlington: Morgan Kaufmann Publishers; 2013. https://doi.org/10.1016/B978-0-12-381479-1.00001-0 .

Book   MATH   Google Scholar  

Arunachalam D, Kumar N. Benefit-based consumer segmentation and performance evaluation of clustering approaches: an evidence of data-driven decision-making. Expert Syst Appl. 2018;111:11–34. https://doi.org/10.1016/J.ESWA.2018.03.007 .

Chase CW. Next generation demand management: people, process, analytics, and technology. Hoboken: Wiley; 2016.

Book   Google Scholar  

SAS Institute. Demand-driven forecasting and planning: take responsiveness to the next level. 13; 2014. https://www.sas.com/content/dam/SAS/en_us/doc/whitepaper2/demand-driven-forecasting-planning-107477.pdf .

Acar Y, Gardner ES. Forecasting method selection in a global supply chain. Int J Forecast. 2012;28(4):842–8. https://doi.org/10.1016/J.IJFORECAST.2011.11.003 .

Ma S, Fildes R, Huang T. Demand forecasting with high dimensional data: the case of SKU retail sales forecasting with intra- and inter-category promotional information. Eur J Oper Res. 2016;249(1):245–57. https://doi.org/10.1016/J.EJOR.2015.08.029 .

Addo-Tenkorang R, Helo PT. Big data applications in operations/supply-chain management: a literature review. Comput Ind Eng. 2016;101:528–43. https://doi.org/10.1016/J.CIE.2016.09.023 .

Agrawal S, Singh RK, Murtaza Q. A literature review and perspectives in reverse logistics. Resour Conserv Recycl. 2015;97:76–92. https://doi.org/10.1016/J.RESCONREC.2015.02.009 .

Gunasekaran A, Kumar Tiwari M, Dubey R, Fosso Wamba S. Big data and predictive analytics applications in supply chain management. Comput Ind Eng. 2016;101:525–7. https://doi.org/10.1016/J.CIE.2016.10.020 .

Hazen BT, Skipper JB, Ezell JD, Boone CA. Big data and predictive analytics for supply chain sustainability: a theory-driven research agenda. Comput Ind Eng. 2016;101:592–8. https://doi.org/10.1016/J.CIE.2016.06.030 .

Hofmann E, Rutschmann E. Big data analytics and demand forecasting in supply chains: a conceptual analysis. Int J Logist Manage. 2018;29(2):739–66. https://doi.org/10.1108/IJLM-04-2017-0088 .

Jain A, Sanders NR. Forecasting sales in the supply chain: consumer analytics in the big data era. Int J Forecast. 2019;35(1):170–80. https://doi.org/10.1016/J.IJFORECAST.2018.09.003 .

Jin J, Liu Y, Ji P, Kwong CK. Review on recent advances in information mining from big consumer opinion data for product design. J Comput Inf Sci Eng. 2018;19(1):010801. https://doi.org/10.1115/1.4041087 .

Kumar R, Mahto D. Industrial forecasting support systems and technologies in practice: a review. Glob J Res Eng. 2013;13(4):17–33.

MathSciNet   Google Scholar  

Mishra D, Gunasekaran A, Papadopoulos T, Childe SJ. Big Data and supply chain management: a review and bibliometric analysis. Ann Oper Res. 2016;270(1):313–36. https://doi.org/10.1007/s10479-016-2236-y .

Ren S, Zhang Y, Liu Y, Sakao T, Huisingh D, Almeida CMVB. A comprehensive review of big data analytics throughout product lifecycle to support sustainable smart manufacturing: a framework, challenges and future research directions. J Clean Prod. 2019;210:1343–65. https://doi.org/10.1016/J.JCLEPRO.2018.11.025 .

Singh Jain AD, Mehta I, Mitra J, Agrawal S. Application of big data in supply chain management. Mater Today Proc. 2017;4(2):1106–15. https://doi.org/10.1016/J.MATPR.2017.01.126 .

Souza GC. Supply chain analytics. Bus Horiz. 2014;57(5):595–605. https://doi.org/10.1016/J.BUSHOR.2014.06.004 .

Tiwari S, Wee HM, Daryanto Y. Big data analytics in supply chain management between 2010 and 2016: insights to industries. Comput Ind Eng. 2018;115:319–30. https://doi.org/10.1016/J.CIE.2017.11.017 .

Zhong RY, Newman ST, Huang GQ, Lan S. Big Data for supply chain management in the service and manufacturing sectors: challenges, opportunities, and future perspectives. Comput Ind Eng. 2016;101:572–91. https://doi.org/10.1016/J.CIE.2016.07.013 .

Ramanathan U, Subramanian N, Parrott G. Role of social media in retail network operations and marketing to enhance customer satisfaction. Int J Oper Prod Manage. 2017;37(1):105–23. https://doi.org/10.1108/IJOPM-03-2015-0153 .

Coursera. Supply chain planning. Coursera E-Learning; 2019. https://www.coursera.org/learn/planning .

Villegas MA, Pedregal DJ. Supply chain decision support systems based on a novel hierarchical forecasting approach. Decis Support Syst. 2018;114:29–36. https://doi.org/10.1016/J.DSS.2018.08.003 .

Ma J, Kwak M, Kim HM. Demand trend mining for predictive life cycle design. J Clean Prod. 2014;68:189–99. https://doi.org/10.1016/J.JCLEPRO.2014.01.026 .

Hamiche K, Abouaïssa H, Goncalves G, Hsu T. A robust and easy approach for demand forecasting in supply chains. IFAC-PapersOnLine. 2018;51(11):1732–7. https://doi.org/10.1016/J.IFACOL.2018.08.206 .

Da Veiga CP, Da Veiga CRP, Catapan A, Tortato U, Da Silva WV. Demand forecasting in food retail: a comparison between the Holt-Winters and ARIMA models. WSEAS Trans Bus Econ. 2014;11(1):608–14.

Murray PW, Agard B, Barajas MA. Forecasting supply chain demand by clustering customers. IFAC-PapersOnLine. 2015;48(3):1834–9. https://doi.org/10.1016/J.IFACOL.2015.06.353 .

Ramos P, Santos N, Rebelo R. Performance of state space and ARIMA models for consumer retail sales forecasting. Robot Comput Integr Manuf. 2015;34:151–63. https://doi.org/10.1016/J.RCIM.2014.12.015 .

Schaer O, Kourentzes N. Demand forecasting with user-generated online information. Int J Forecast. 2019;35(1):197–212. https://doi.org/10.1016/J.IJFORECAST.2018.03.005 .

Pang Y, Yao B, Zhou X, Zhang Y, Xu Y, Tan Z. Hierarchical electricity time series forecasting for integrating consumption patterns analysis and aggregation consistency; 2018. In: IJCAI international joint conference on artificial intelligence; 2018, p. 3506–12.

Goyal R, Chandra P, Singh Y. Suitability of KNN regression in the development of interaction based software fault prediction models. IERI Procedia. 2014;6:15–21. https://doi.org/10.1016/J.IERI.2014.03.004 .

Runkler TA. Data analytics (models and algorithms for intelligent data analysis). In: Revista Espanola de las Enfermedades del Aparato Digestivo (Vol. 26, Issue 4). Springer Fachmedien Wiesbaden; 2016. https://doi.org/10.1007/978-3-658-14075-5 .

Nikolopoulos KI, Babai MZ, Bozos K. Forecasting supply chain sporadic demand with nearest neighbor approaches. Int J Prod Econ. 2016;177:139–48. https://doi.org/10.1016/j.ijpe.2016.04.013 .

Gaur M, Goel S, Jain E. Comparison between nearest Neighbours and Bayesian network for demand forecasting in supply chain management. In: 2015 international conference on computing for sustainable global development, INDIACom 2015, May; 2015, p. 1433–6.

Burney SMA, Ali SM, Burney S. A survey of soft computing applications for decision making in supply chain management. In: 2017 IEEE 3rd international conference on engineering technologies and social sciences, ICETSS 2017, 2018, p. 1–6. https://doi.org/10.1109/ICETSS.2017.8324158 .

González Perea R, Camacho Poyato E, Montesinos P, Rodríguez Díaz JA. Optimisation of water demand forecasting by artificial intelligence with short data sets. Biosyst Eng. 2019;177:59–66. https://doi.org/10.1016/J.BIOSYSTEMSENG.2018.03.011 .

Vhatkar S, Dias J. Oral-care goods sales forecasting using artificial neural network model. Procedia Comput Sci. 2016;79:238–43. https://doi.org/10.1016/J.PROCS.2016.03.031 .

Wong WK, Guo ZX. A hybrid intelligent model for medium-term sales forecasting in fashion retail supply chains using extreme learning machine and harmony search algorithm. Int J Prod Econ. 2010;128(2):614–24. https://doi.org/10.1016/J.IJPE.2010.07.008 .

Liu C, Shu T, Chen S, Wang S, Lai KK, Gan L. An improved grey neural network model for predicting transportation disruptions. Expert Syst Appl. 2016;45:331–40. https://doi.org/10.1016/J.ESWA.2015.09.052 .

Yuan WJ, Chen JH, Cao JJ, Jin ZY. Forecast of logistics demand based on grey deep neural network model. Proc Int Conf Mach Learn Cybern. 2018;1:251–6. https://doi.org/10.1109/ICMLC.2018.8527006 .

Amirkolaii KN, Baboli A, Shahzad MK, Tonadre R. Demand forecasting for irregular demands in business aircraft spare parts supply chains by using artificial intelligence (AI). IFAC-PapersOnLine. 2017;50(1):15221–6. https://doi.org/10.1016/J.IFACOL.2017.08.2371 .

Huang L, Xie G, Li D, Zou C. Predicting and analyzing e-logistics demand in urban and rural areas: an empirical approach on historical data of China. Int J Performabil Eng. 2018;14(7):1550–9. https://doi.org/10.23940/ijpe.18.07.p19.15501559 .

Saha C, Lam SS, Boldrin W. Demand forecasting for server manufacturing using neural networks. In: Proceedings of the 2014 industrial and systems engineering research conference, June 2014; 2015.

Chang P-C, Wang Y-W, Tsai C-Y. Evolving neural network for printed circuit board sales forecasting. Expert Syst Appl. 2005;29(1):83–92. https://doi.org/10.1016/J.ESWA.2005.01.012 .

Merkuryeva G, Valberga A, Smirnov A. Demand forecasting in pharmaceutical supply chains: a case study. Procedia Comput Sci. 2019;149:3–10. https://doi.org/10.1016/J.PROCS.2019.01.100 .

Yang CL, Sutrisno H. Short-term sales forecast of perishable goods for franchise business. In: 2018 10th international conference on knowledge and smart technology: cybernetics in the next decades, KST 2018, p. 101–5; 2018. https://doi.org/10.1109/KST.2018.8426091 .

Villegas MA, Pedregal DJ, Trapero JR. A support vector machine for model selection in demand forecasting applications. Comput Ind Eng. 2018;121:1–7. https://doi.org/10.1016/J.CIE.2018.04.042 .

Wu Q. The hybrid forecasting model based on chaotic mapping, genetic algorithm and support vector machine. Expert Syst Appl. 2010;37(2):1776–83. https://doi.org/10.1016/J.ESWA.2009.07.054 .

Guanghui W. Demand forecasting of supply chain based on support vector regression method. Procedia Eng. 2012;29:280–4. https://doi.org/10.1016/J.PROENG.2011.12.707 .

Sarhani M, El Afia A. Intelligent system based support vector regression for supply chain demand forecasting. In: 2014 2nd world conference on complex systems, WCCS 2014; 2015, p. 79–83. https://doi.org/10.1109/ICoCS.2014.7060941 .

Chen IF, Lu CJ. Sales forecasting by combining clustering and machine-learning techniques for computer retailing. Neural Comput Appl. 2017;28(9):2633–47. https://doi.org/10.1007/s00521-016-2215-x .

Fasli M, Kovalchuk Y. Learning approaches for developing successful seller strategies in dynamic supply chain management. Inf Sci. 2011;181(16):3411–26. https://doi.org/10.1016/J.INS.2011.04.014 .

Islek I, Oguducu SG. A retail demand forecasting model based on data mining techniques. In: IEEE international symposium on industrial electronics; 2015, p. 55–60. https://doi.org/10.1109/ISIE.2015.7281443 .

Kilimci ZH, Akyuz AO, Uysal M, Akyokus S, Uysal MO, Atak Bulbul B, Ekmis MA. An improved demand forecasting model using deep learning approach and proposed decision integration strategy for supply chain. Complexity. 2019;2019:1–15. https://doi.org/10.1155/2019/9067367 .

Loureiro ALD, Miguéis VL, da Silva LFM. Exploring the use of deep neural networks for sales forecasting in fashion retail. Decis Support Syst. 2018;114:81–93. https://doi.org/10.1016/J.DSS.2018.08.010 .

Punam K, Pamula R, Jain PK. A two-level statistical model for big mart sales prediction. In: 2018 international conference on computing, power and communication technologies, GUCON 2018; 2019. https://doi.org/10.1109/GUCON.2018.8675060 .

Puspita PE, İnkaya T, Akansel M. Clustering-based Sales Forecasting in a Forklift Distributor. In: Uluslararası Muhendislik Arastirma ve Gelistirme Dergisi, 1–17; 2019. https://doi.org/10.29137/umagd.473977 .

Thomassey S. Sales forecasts in clothing industry: the key success factor of the supply chain management. Int J Prod Econ. 2010;128(2):470–83. https://doi.org/10.1016/J.IJPE.2010.07.018 .

Brentan BM, Ribeiro L, Izquierdo J, Ambrosio JK, Luvizotto E, Herrera M. Committee machines for hourly water demand forecasting in water supply systems. Math Probl Eng. 2019;2019:1–11. https://doi.org/10.1155/2019/9765468 .

Mafakheri F, Breton M, Chauhan S. Project-to-organization matching: an integrated risk assessment approach. Int J IT Project Manage. 2012;3(3):45–59. https://doi.org/10.4018/jitpm.2012070104 .

Mafakheri F, Nasiri F. Revenue sharing coordination in reverse logistics. J Clean Prod. 2013;59:185–96. https://doi.org/10.1016/J.JCLEPRO.2013.06.031 .

Bogataj M. Closed Loop Supply Chain (CLSC): economics, modelling, management and control. Int J Prod Econ. 2017;183:319–21. https://doi.org/10.1016/J.IJPE.2016.11.020 .

Hopkins J, Hawking P. Big Data Analytics and IoT in logistics: a case study. Int J Logist Manage. 2018;29(2):575–91. https://doi.org/10.1108/IJLM-05-2017-0109 .

de Oliveira CM, Soares PJSR, Morales G, Arica J, Matias IO. RFID and its applications on supply chain in Brazil: a structured literature review (2006–2016). Espacios. 2017;38(31). https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021922345&partnerID=40&md5=f062191611541391ded4cdb73eea55cb .

Griva A, Bardaki C, Pramatari K, Papakiriakopoulos D. Retail business analytics: customer visit segmentation using market basket data. Expert Syst Appl. 2018;100:1–16. https://doi.org/10.1016/J.ESWA.2018.01.029 .

Lee CKM, Ho W, Ho GTS, Lau HCW. Design and development of logistics workflow systems for demand management with RFID. Expert Syst Appl. 2011;38(5):5428–37. https://doi.org/10.1016/J.ESWA.2010.10.012 .

Mohebi E, Marquez L. Application of machine learning and RFID in the stability optimization of perishable foods; 2008.

Jiao Z, Ran L, Zhang Y, Li Z, Zhang W. Data-driven approaches to integrated closed-loop sustainable supply chain design under multi-uncertainties. J Clean Prod. 2018;185:105–27.

Levis AA, Papageorgiou LG. Customer demand forecasting via support vector regression analysis. Chem Eng Res Des. 2005;83(8):1009–18. https://doi.org/10.1205/CHERD.04246 .

Chi H-M, Ersoy OK, Moskowitz H, Ward J. Modeling and optimizing a vendor managed replenishment system using machine learning and genetic algorithms. Eur J Oper Res. 2007;180(1):174–93. https://doi.org/10.1016/J.EJOR.2006.03.040 .

Sun Z-L, Choi T-M, Au K-F, Yu Y. Sales forecasting using extreme learning machine with applications in fashion retailing. Decis Support Syst. 2008;46(1):411–9. https://doi.org/10.1016/J.DSS.2008.07.009 .

Efendigil T, Önüt S, Kahraman C. A decision support system for demand forecasting with artificial neural networks and neuro-fuzzy models: a comparative analysis. Expert Syst Appl. 2009;36(3):6697–707. https://doi.org/10.1016/J.ESWA.2008.08.058 .

Lee CC, Ou-Yang C. A neural networks approach for forecasting the supplier’s bid prices in supplier selection negotiation process. Expert Syst Appl. 2009;36(2):2961–70. https://doi.org/10.1016/J.ESWA.2008.01.063 .

Chen F-L, Chen Y-C, Kuo J-Y. Applying Moving back-propagation neural network and Moving fuzzy-neuron network to predict the requirement of critical spare parts. Expert Syst Appl. 2010;37(9):6695–704. https://doi.org/10.1016/J.ESWA.2010.04.037 .

Wu Q. Product demand forecasts using wavelet kernel support vector machine and particle swarm optimization in manufacture system. J Comput Appl Math. 2010;233(10):2481–91. https://doi.org/10.1016/J.CAM.2009.10.030 .

Babai MZ, Ali MM, Boylan JE, Syntetos AA. Forecasting and inventory performance in a two-stage supply chain with ARIMA(0,1,1) demand: theory and empirical analysis. Int J Prod Econ. 2013;143(2):463–71. https://doi.org/10.1016/J.IJPE.2011.09.004 .

Kourentzes N. Intermittent demand forecasts with neural networks. Int J Prod Econ. 2013;143(1):198–206. https://doi.org/10.1016/J.IJPE.2013.01.009 .

Lau HCW, Ho GTS, Zhao Y. A demand forecast model using a combination of surrogate data analysis and optimal neural network approach. Decis Support Syst. 2013;54(3):1404–16. https://doi.org/10.1016/J.DSS.2012.12.008 .

Arunraj NS, Ahrens D. A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting. Int J Prod Econ. 2015;170:321–35. https://doi.org/10.1016/J.IJPE.2015.09.039 .

Di Pillo G, Latorre V, Lucidi S, Procacci E. An application of support vector machines to sales forecasting under promotions. 4OR. 2016. https://doi.org/10.1007/s10288-016-0316-0 .

da Veiga CP, da Veiga CRP, Puchalski W, dos Coelho LS, Tortato U. Demand forecasting based on natural computing approaches applied to the foodstuff retail segment. J Retail Consumer Serv. 2016;31:174–81. https://doi.org/10.1016/J.JRETCONSER.2016.03.008 .

Chawla A, Singh A, Lamba A, Gangwani N, Soni U. Demand forecasting using artificial neural networks—a case study of American retail corporation. In: Applications of artificial intelligence techniques in wind power generation. Integrated Computer-Aided Engineering; 2018, p. 79–90. https://doi.org/10.3233/ica-2001-8305 .

Pereira MM, Machado RL, Ignacio Pires SR, Pereira Dantas MJ, Zaluski PR, Frazzon EM. Forecasting scrap tires returns in closed-loop supply chains in Brazil. J Clean Prod. 2018;188:741–50. https://doi.org/10.1016/J.JCLEPRO.2018.04.026 .

Fanoodi B, Malmir B, Jahantigh FF. Reducing demand uncertainty in the platelet supply chain through artificial neural networks and ARIMA models. Comput Biol Med. 2019;113:103415. https://doi.org/10.1016/J.COMPBIOMED.2019.103415 .

Sharma R, Singhal P. Demand forecasting of engine oil for automotive and industrial lubricant manufacturing company using neural network. Mater Today Proc. 2019;18:2308–14. https://doi.org/10.1016/J.MATPR.2019.07.013 .

Tanizaki T, Hoshino T, Shimmura T, Takenaka T. Demand forecasting in restaurants using machine learning and statistical analysis. Procedia CIRP. 2019;79:679–83. https://doi.org/10.1016/J.PROCIR.2019.02.042 .

Wang C-H, Chen J-Y. Demand forecasting and financial estimation considering the interactive dynamics of semiconductor supply-chain companies. Comput Ind Eng. 2019;138:106104. https://doi.org/10.1016/J.CIE.2019.106104 .

Download references

Acknowledgements

The authors are very much thankful to anonymous reviewers whose comments and suggestion were very helpful in improving the quality of the manuscript.

Author information

Authors and affiliations.

Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, H3G 1M8, Canada

Mahya Seyedan & Fereshteh Mafakheri

You can also search for this author in PubMed   Google Scholar

Contributions

The authors contributed equally to the writing of the paper. First author conducted the literature search. Both authors read and approved the final manuscript.

Corresponding author

Correspondence to Fereshteh Mafakheri .

Ethics declarations

Ethics approval.

Not applicable.

Competing interests

The authors declare no competing or conflicting interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Seyedan, M., Mafakheri, F. Predictive big data analytics for supply chain demand forecasting: methods, applications, and research opportunities. J Big Data 7 , 53 (2020). https://doi.org/10.1186/s40537-020-00329-2

Download citation

Received : 05 April 2020

Accepted : 17 July 2020

Published : 25 July 2020

DOI : https://doi.org/10.1186/s40537-020-00329-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Demand forecasting
• Closed-loop supply chains
• Machine-learning

Page One Economics ®

The science of supply and demand.

"A body in motion tends to stay in motion unless acted on by an out-side force."  

—Isaac Newton

Science Is Everywhere

We live in a world governed by the laws of science. From gravity, to electromagnetism, to sound waves, our lives are filled with scientific phenomena that structure and affect every facet of our daily routine. As a species, we have attempted at every turn to channel the laws of science to our own benefit, constantly working to build better products and to develop improved means of manufacturing. However, sometimes science unveils itself in unanticipated ways—ways that often force its will on the distribution of goods in markets.

Figure 1 Personal Consumption Expenditures

SOURCE: FRED ® , Federal Reserve Bank of St Louis; https://fred.stlouisfed.org/graph/?g=r60z , accessed January 2021.

Few events demonstrate this fact better than the COVID-19 pandemic of 2020. As this new viral strain spread around the globe, many businesses in the United States closed or reduced workers' hours, sometimes by the choice of businesses—to prevent employees from catching the virus—and sometimes due to government stay-at-home orders. 1 In the early months of the pandemic, virtually no industry or market remained unaffected as the economy declined: Consumer spending on goods and services dropped by 6.7 percent in March and 12.7 percent in April (Figure 1) and the unemployment rate rose from a 50-year low of 3.5 percent in February to a post-Great Depression record of 14.7 percent in April (Figure 2). 

Figure 2 Unemployment Rate

SOURCE: FRED ® , Federal Reserve Bank of St. Louis; https://fred.stlouisfed.org/graph/?g=r5AM , accessed January 2021.

Supply and Demand

COVID-19 affected markets the same way they are affected by any outside force—through supply and demand . In competitive markets , supply and demand govern the ways that buyers and sellers determine how much of a good or service to trade in reaction to price changes.

The law of demand describes the behavior of buyers in markets: As the price (P) of a good or service rises, the quantity demanded (Q D ) of that good or service falls. Likewise, as the price of a good or service falls, the quantity demanded of that good or service rises. Consider your favorite snack food. A downward sloping demand curve indicates that as the price of the snack increases, you would be able and/or willing to buy a smaller amount. This relationship is demonstrated by the downward sloping demand curve in Figure 3. When the price increases from P 1 to P 2 , the quantity demanded decreases from Q 1 to Q 2 .

Similarly, the law of supply describes the behavior of sellers in markets: As the price of a good or service rises, the quantity supplied of that good or service rises. Like­wise, as the price of a good or service falls, the quantity supplied of that good or service falls. Therefore, as the price (as determined by the market) of your favorite snack rises, firms are willing to produce more units. This relationship is demonstrated by the graph of the upward sloping supply curve in Figure 4. When the price increases from P 1 to P 2 , firms are willing to supply a greater quantity. That is, the quantity supplied increases from Q 1 to Q 2 .

Market prices are constantly adjusting to bring into balance the amount desired by buyers and the amount sold by sellers. This balance is found at the equilibrium price , where supply and demand intersect (Figure 5). At this point we have our equilibrium price (P e ) and equilibrium quantity (Q e ).

Scientific Events

Biology: COVID-19

The COVID-19 pandemic and the associated lockdowns hit the Leisure and Hospitality sector particularly hard (Figure 6). A recent study looked at hours worked by sector in the immediate aftermath of stay-at-home orders—March 2020. 2 As shown in Figure 6, the effects on hours worked are separated into supply factors (red bars) and demand factors (blue bars) and measured as the percent change in historical growth rates of hours worked in each sector. Supply factors are related to businesses partially or fully shutting down. Demand factors are related to reduced consumer spending, such as from customers not shopping, to avoid catching the virus, or simply cutting back on spending due to income loss. 3 For most sectors, hours worked dropped compared with historical trends due to both supply and demand factors.

When a factor other than price affects supply or demand, it is modeled by shifting the supply or demand curve, respectively, rather than moving along the curve. For increases in supply or demand, the curves are shifted to the right to higher quantities. For decreases, the curves are shifted to the left to lower quantities.

Although supply factors contributed to most of the almost 10 percent drop in the Leisure and Hospitality sector in March 2020 compared with historical growth, demand factors also contributed (see Figure 6). The change in this sector is demonstrated in Figure 7: Demand decreases (shifts to the left) and supply decreases more (also shifts to the left), resulting in a lower quantity of goods sold at the new equilibrium (Q 2 ). 4

Meteorology: Hurricane Sandy

In the fall of 2012, Hurricane Sandy hit New York City and surrounding regions, with millions of citizens and thousands of businesses losing power. In New Jersey, only 40 percent of gas stations tracked by AAA had power and were operational in the immediate aftermath of the hurricane. 5 As a result, consumers faced a severe shock to the supply of gasoline.

Applying the laws of supply and demand, one can predict how this event would change the quantity and price of gasoline at the pump: Assuming unchanged demand, 6 the supply curve would shift to the left (Figure 8). The equilibrium quantity would decrease from Q 1 to Q 2 , with the price increasing from P 1 to P 2 .

Did this occur? Not exactly. New Jersey Governor Chris Christie promised to punish gas stations that significantly increased prices above their pre-hurricane levels (P 1 ). 7 As a result, prices remained low because they were not allowed to reach equilibrium, so oil firms had no incentive to bring extra gasoline to the market at the lower price, long lines of vehicles formed, and many stations sold out due to limited supply. 

Chemistry: The Ethanol Fuel Boom

In the late 2000s, ethanol experienced a boom as an alternative fuel. Compared with gasoline, ethanol was believed to be cleaner burning (produce less carbon dioxide) and could be produced from renewable crops such as corn and sugar cane. 8 With subsidies provided by the U.S. government to produce fuel ethanol, production facilities sprouted up across the Midwest and supply increased in this growing industry. 9

With more and more ethanol being blended into gasoline for use in everyday car engines, many believed that yearly production would continue to grow for years to come. Then, consumers began noticing that their gas engines were being damaged by gasoline mixtures with large percentages of ethanol. 10 As it turns out, the chemical nature of ethanol makes it very attractive to water. When water gets into an engine's fuel, it increases the corrosion of metal and degrades the engine. As a result, regulators decided that gasoline for normal car engines could only contain up to 10 percent ethanol by volume. 11,12

Using supply and demand to analyze fuel ethanol markets is a little tricky due to the volume ethanol limit. In Figure 9, the desire of producers to increase the supply of ethanol is indicated by the rightward shift of the supply curve. Producers would expect ethanol buyers to continue increasing their demand as ethanol becomes more and more popular. However, all else being equal, once buyers are running their vehicles with gasoline with 10 percent ethanol, their desire to purchase more would dramatically decrease and the demand curve would become a nearly straight vertical line. 13 That is, the quantity demanded wouldn't increase much beyond this limit even if the price of ethanol were to decrease because people won't use gasoline with more than 10 percent ethanol. Thus, no matter how much producers wish to increase supply, buyers would not buy much more ethanol and increased production of ethanol would drive down prices.

Figure 10 U.S. Fuel Ethanol Consumption and Percent of Motor Gasoline Consumption, 1981-2019 (June 24, 2020)

Figure 10 confirms this analysis of supply and demand. Fuel ethanol consumption increased dramatically during the 2000s and then flattened out when it reached about 10 percent of motor gasoline consumption. 14

Markets provide a means by which individuals and businesses can trade goods and services. Though goods and services come in many shapes and sizes, they are all governed by the laws of supply and demand. Of course, unanticipated scientific events, such as pandemics and hurricanes, can alter the course of markets. Yet, the same laws that make markets function every day will exert their will—the laws of supply and demand.

https://www.sciencemag.org/news/2020/03/modelers-weigh-value-lives-and-lockdown-costs-put-price-covid-19 .

2 Brinca, Pedro; Duarte, Joao B.  and Faria-e-Castro, Miguel. "Is the COVID-19 Pandemic a Supply or a Demand Shock?" Federal Reserve Bank of St. Louis Economic Synopses , 2020, No. 31; https://research.stlouisfed.org/publications/economic-synopses/2020/05/20/is-the-covid-19-pandemic-a-supply-or-a-demand-shock .

3 Some sectors such as Wholesale Trade and Information were positively impacted by demand factors. In the case of the Information sector, the increase may have been caused by families increasing their demand for goods and services to work, communicate, and/or enjoy entertainment from home.

4 Figure 7 depicts price increasing, but price could decrease depending on the size of the supply and demand shifts and how responsive supply and demand are to price changes. 

5 Smith, Aaron. "Gas Shortage Continues in Areas Hit By Sandy." CNN Business, November 2, 2012; https://money.cnn.com/2012/11/02/news/economy/gas-shortage-sandy/index.html .

6 There could actually have been an increase in demand from individuals using gas powered electric generators during the power outage.

7 Futrelle, David. "Post-Sandy Price Gouging: Economically Sound, Ethically Dubious." Time , November 2, 2012; https://business.time.com/2012/11/02/post-sandy-price-gouging-economically-sound-ethically-dubious/ .

8 U.S. Energy Information Administration. "Biofuels Explained: Ethanol and the Environment." December 7, 2020, update; https://www.eia.gov/energyexplained/biofuels/ethanol-and-the-environment.php .

9 Byrge, Joshua A. and Kliesen, Kevin L. "Ethanol: Economic Gain or Drain?" Federal Reserve Bank of St. Louis Regional Economist , July 1, 2008; https://www.stlouisfed.org/publications/regional-economist/july-2008/ethanol-economic-gain-or-drain .

10 Johnson, M. Alex. "Mechanics See Ethanol Damaging Small Engines." NBC News, August 1, 2008; https://www.nbcnews.com/id/wbna25936782 .

11 Tyner, Wallace E.; Brechbil, Sarah l. and Perkis, David. "Cellulosic Ethanol: Feed­stocks, Conversion Technologies, Economics, and Policy Options." Congressional Research Service, October 22, 2010; http://nationalaglawcenter.org/wp-content/uploads/assets/crs/R41460.pdf .

12 Specialty vehicles with anti-corrosive engine parts were sold to accommodate fuel with higher concentrations of ethanol, including E85, a fuel mixture containing 85 percent ethanol. However, such vehicles and fuel types have yet to gain mass popularity.

13 The demand curve would likely not be fully vertical, as decreases in any fuel component's price, like ethanol's, would increase the quantity demanded of fuel. However, because ethanol makes up a small percentage of fuel, the demand curve is assumed to be nearly vertical.

14 U.S. Energy Information Administration (2020). See footnote 8.

© 2021, Federal Reserve Bank of St. Louis. The views expressed are those of the author(s) and do not necessarily reflect official positions of the Federal Reserve Bank of St. Louis or the Federal Reserve System.

Biology: The study of living organisms.

Chemistry: The branch of science that deals with the identification of the substances of which matter is composed.

Competitive markets: Markets in which there are generally many buyers and many sellers so that each has a negligible impact on market prices.

Demand: The quantity of a good or service that buyers are willing and able to buy at all possible prices during a certain time period.

Equilibrium price: The price at which quantity supplied and quantity demanded are equal. The point at which the supply and demand curves intersect.

Meteorology: The branch of science concerned with the processes and phenomena of the atmosphere, especially as a means of forecasting the weather.

Subsidies: Payments made by the government to support businesses or markets. No goods or services are provided in return for the payments.

Supply: The quantity of a good or service that producers are willing and able to sell at all possible prices during a certain time period.

Cite this article

Subscribe to Our Newsletter

Stay current with brief essays, scholarly articles, data news, and other information about the economy from the Research Division of the St. Louis Fed.

SUBSCRIBE TO THE RESEARCH DIVISION NEWSLETTER

Research division.

• Legal and Privacy

One Federal Reserve Bank Plaza St. Louis, MO 63102

Information for Visitors

Demand Forecasting : Literature Review On Various Methodologies

Ieee account.

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Economic Effects of Tighter Lending by Banks

Download PDF (299 KB)

FRBSF Economic Letter 2024-11 | May 6, 2024

Banks tightened the criteria used to approve loans over the past year. Analysis shows that their tighter lending standards can be partially explained by economic conditions that reduce demand for loans and increase their potential risk, such as policy rate increases and a slowing economy. The unexplained part may reflect a restrained credit supply, specifically related to banks being less willing or able to take on risk. What are the potential economic consequences? Past credit supply shocks have had significant long-lasting effects on unemployment but less impact on inflation.

The first half of 2023 was characterized by credit market turbulence, including the collapse of Silicon Valley Bank, Signature Bank, and others. The increased uncertainty in the banking sector that followed these closures led many banks to tighten their credit standards, becoming stricter about the conditions under which they were willing to lend. According to the Senior Loan Officer Opinion Survey on Bank Lending Practices (SLOOS), lending standards in 2023 tightened to a degree only seen during the Global Financial Crisis and the COVID-19 pandemic. This leads to questions about the possible effects on the overall economy, particularly whether tighter standards resulted from an unexpected drop in the credit supply or other economic factors, such as higher interest rates or a slowing of the economy.

In this Economic Letter , I analyze supply and demand factors in credit market conditions and their impact on bank lending standards, like Lown and Morgan (2006) and others. A measure based on reports from bank loan officers shows that credit conditions began tightening in mid-2022, well before the bank closures. Since early 2023, about half of the tightening in lending standards has been due to changes in the credit supply specific to the banking sector, such as banks reevaluating their willingness to take on risk, and the remainder in response to other economic conditions. My analysis also estimates that unexpected changes to credit supply conditions—including the March 2023 bank closures—can account for 0.4 percentage point of unemployment by the end of 2023, meaning that unemployment in that quarter would have been 3.3% without the credit supply shock. My estimates suggest that the effects related to these credit supply shocks will be persistent, lasting through 2026. The contribution of these shocks to inflation is likely to be more subdued, pushing core personal consumption expenditures (PCE) inflation down by less than a 0.1 percentage point through 2026.

Bank lending standards and the economy

Bank lending to businesses depends on two key components: the loan interest rate and the lending standards that businesses need to meet to qualify for a loan. When banks are more willing to take on risk, they impose minimal lending standards; by contrast, when banks prefer to take on less risk, they scrutinize borrowers more and impose stricter conditions. The interest rate on loans responds to both credit supply and credit demand conditions. By contrast, lending standards are more directly related to the willingness or ability of banks to tolerate risk. Thus, they can be used as a proxy for credit supply conditions.

Using SLOOS data, I measure commercial and industrial bank lending conditions as the percentage of responding banks that report tighter lending standards minus the percentage that report easing of lending standards. The resulting measure can range from –100, meaning that all banks are easing standards, to 100, meaning that all banks are tightening standards. A positive (negative) number means that it is harder (easier) for firms to get credit. This method has been used by Lown and Morgan (2006) and other studies to measure credit supply conditions. Figure 1 shows the evolution of this measure from 2007 through 2023 for lending to medium and large businesses (blue line) and to small businesses (green line).

Figure 1 Tightening in commercial and industrial lending standards

The figure shows that lending standards tightened in 2023 to a degree seen only during the Global Financial Crisis in 2008 and the onset of the COVID-19 pandemic in 2020. It also clearly shows that lending standards began tightening in the second half of 2022, well before the bank collapses in early 2023. Finally, the tightening in 2023 lending standards was very similar for all businesses regardless of their size. Therefore, I use the measure for medium and large firms as representative for the economy.

I use this measure in statistical analysis to estimate how credit conditions interact with the rest of the economy, particularly to understand their impact on unemployment and inflation. To measure unemployment, I focus on the unemployment gap, calculated as the difference between the measured unemployment rate and the Congressional Budget Office measure of the potential unemployment rate, and I use the core personal consumption expenditures (PCE) price index to measure inflation.

My approach builds on the work of Lown and Morgan (2006), combining this measure of credit conditions with other measures of financial conditions. These include the effective federal funds rate, the 10-year Treasury constant maturity yield, the 30-year fixed mortgage rate spread relative to the 10-year Treasury yield, the BAA corporate bonds yield spread relative to 10-year Treasury bonds, and bank loans. Finally, to reflect forces that have recently been important in shaping the economy and inflation—namely supply chain pressures and significant changes in energy prices—I also include the West Texas Intermediate spot oil price, and the Federal Reserve Bank of New York’s Global Supply Chain Pressures Index. The analysis uses data from 1998 through the second quarter of 2023.

My statistical model considers interactions between the different variables within the same quarter and over time. The SLOOS lending standards measure is observed early in the quarter and corresponds to bank responses from the previous quarter. Shocks to this measure are thus identified as changes in lending standards that do not respond to other variables within the same quarter. That is, tightening of standards can respond to this identified shock in the same quarter, and to other types of shocks from previous quarters.

Figure 2 shows how much a 10 percentage point tightening in lending standards affects the unemployment gap and inflation. The horizontal axis shows the number of quarters since the shock took place. The vertical axis shows the increase in percentage points for each variable relative to the absence of tighter lending standards, with zero meaning no change in outcomes. The solid blue line is the median estimate, and the shaded areas represent the 70% (darker) and 90% (lighter) probability ranges of possible estimates.

Figure 2 Response of unemployment and inflation to a 10 percentage point tightening of lending standards

Note: Shading represents 70% (darker) and 90% (lighter) probability estimates around median estimate. Source: Senior Loan Officer Opinion Survey on Bank Lending Practices and author’s calculations.

Overall, the tightening in lending standards induces a persistent increase in the unemployment gap and a small drop in inflation. The impact on unemployment is expected: tighter lending standards imply that firms cannot invest as much, reducing demand for credit in the economy. With weaker demand, firms will hire fewer workers and lay off some of their workforce, leading to higher unemployment.

The impact on inflation is more nuanced. On the one hand, a weaker demand for credit eases price inflation. On the other hand, as documented in Gilchrist and Zakrajsek (2012), tighter lending standards are also associated with higher interest rates, which increase operational costs for firms. Firms will pass some of those higher costs to their customers, leading to price inflation. Model estimates suggest the demand effect is more likely to prevail, and inflation falls slightly on net in response to tighter lending standards.

What led to tight lending standards in 2023?

Was the 2023 tightening in lending standards a pure credit supply shock, or was it a natural response of banks to evolving economic conditions? To address this question, I compare actual data at each point in time with the model’s predictions for that time to extract each component’s response to past shocks. I use the results to determine how much of the actual response of each component is due to shocks of different sources—for example, how much of the changing lending standards comes from responses to supply chain shocks or credit supply shocks.

The analysis suggests that credit supply shocks account for about 23 percentage points of the tighter lending standards in the first half of 2023. The remaining 22 percentage points of the tightening is associated with the response of lending standards to changes in economic conditions due to supply chain pressures and other factors originating outside the credit market.

The measure also shows that lending standards started to tighten before 2023, as early as the second quarter of 2022, as shown in Figure 1. This suggests that inflationary pressures and monetary policy tightening in previous quarters played a role in banking conditions more generally. Therefore, tighter credit standards may be related to the bank collapses in that they shared similar root causes in recent economic and financial conditions. However, credit supply factors in the first half of 2023 that could be associated with bank closures explain only part of the overall tightening of lending standards. Furthermore, my model estimates that the impact of the credit supply shock on tighter lending standards will be relatively short lived, dissipating by the end of 2024.

I next use this methodology to estimate how much credit supply shocks contributed to unemployment and inflation in the recent past and how much they are expected to contribute through 2026. To do this, I combine the estimated size of the shocks with the estimated responses of the economy to those shocks. The bars in Figure 3 show the median estimated contribution to unemployment.

Figure 3 Contribution of credit supply shocks to unemployment

The estimated contribution for the last quarter of 2023 is 0.4 percentage point, which means that unemployment would have been 3.3% without the credit supply shock, rather than the 3.7% reported in the data. My analysis shows that, even though the tightening of lending standards is not expected to last long, the effects on unemployment are estimated to persist through 2026. For inflation, the contribution of the credit supply shock is more subdued but more persistent, pulling inflation down by less than 0.1 percentage point through the entire projection into 2026. A persistent increase in corporate bond yield spreads implied by the credit supply shock may explain why the effects on the rest of the economy last so long.

This analysis has several limitations, including the possibility that underlying economic relations changed with the COVID-19 pandemic. Related to this, the model is proportional, implying that a shock of twice the size would have effects that are also twice the reported size. However, the unusually large shocks in this analysis could trigger more than proportional economic responses—for example, if cascading bank failures induced snowball effects in the economy due to an increasingly fragile banking system. Finally, using different measures to proxy for financial and monetary policy conditions could result in different estimates, although my tests using different data yielded similar results to those reported here.

In the first half of 2023, lending standards tightened substantially. This Letter finds that only about half of the tightening resulted from a credit supply shock that would have caused a slowdown in economic activity, while the remainder corresponds to banks’ normal response to overall economic conditions. While a tightening of lending standards is not expected to persist for very long, this analysis suggests it could add half a percentage point to unemployment through 2024 and push down inflation by a small amount.

Lown, Cara, and Donald P. Morgan. 2006. “The Credit Cycle and the Business Cycle: New Findings Using the Loan Officer Opinion Survey.” Journal of Money Credit and Banking 38(6).

Simon Gilchrist and Egon Zakrajsek. 2012. “Credit Spreads and Business Cycle Fluctuations.” American Economic Review 102(4, June), pp. 1,692–1,720.

Opinions expressed in FRBSF Economic Letter do not necessarily reflect the views of the management of the Federal Reserve Bank of San Francisco or of the Board of Governors of the Federal Reserve System. This publication is edited by Anita Todd and Karen Barnes. Permission to reprint portions of articles or whole articles must be obtained in writing. Please send editorial comments and requests for reprint permission to [email protected]

Create an account

Create a free IEA account to download our reports or subcribe to a paid service.

More efficient and flexible buildings are key to clean energy transitions

Cite commentary

IEA (2024), More efficient and flexible buildings are key to clean energy transitions , IEA, Paris https://www.iea.org/commentaries/more-efficient-and-flexible-buildings-are-key-to-clean-energy-transitions, Licence: CC BY 4.0

Share this commentary

• Share on Twitter Twitter
• Share on Facebook Facebook
• Share on LinkedIn LinkedIn
• Share on Email Email
• Share on Print Print

People spend the vast majority of their time in buildings, from houses to offices, stores and schools. And while these buildings serve different purposes, they all have at least one thing in common: To keep the lights on, run heating and cooling systems, and use appliances and equipment, they require substantial amounts of energy. Buildings today account for about 30% of final energy consumption globally and more than half of final electricity demand.

The sector is growing rapidly, especially in developing economies. Expanding electricity access and rising incomes mean that more people are buying appliances such as air conditioners – and as temperatures rise, they’re running them more often. However, with a greater focus on well-tested energy efficiency policies, energy consumption from the sector could be significantly reduced, all while maintaining – or even improving – the quality of energy services delivered. This would not only lower the building sector’s emissions, but also save money for energy consumers.

Leveraging technologies that allow buildings to use energy more flexibly throughout the day could unlock even greater benefits. When buildings and grids can communicate with each other, stress during peak times can be mitigated and peaks in energy demand can be smoothed out. As global floor area booms, prioritising both efficiency and flexibility is crucial to the security and sustainability of the world’s energy system.

Electrification and renewables growth are changing how buildings consume energy

Buildings are consuming more energy as economic activity increases and electrification expands, with more heat pumps running in homes and electric vehicles charging in garages. Between 2015 and 2022, residential heat pump sales tripled , and in 2023, electric cars accounted for one in five vehicle sales globally . Currently, most of electric vehicle charging takes place at residences and workplaces .

Adoption of these technologies is crucial to achieve net zero emissions from the energy sector by 2050 and limit global warming to the Paris Agreement target of 1.5 °C, however, it is also driving up electricity demand. Under the IEA’s Stated Policies Scenario , which is based on today's policy settings, peak electricity demand in buildings increases in all regions of the world in the coming decades. In China, it doubles by mid-century, while in the European Union, it increases by two‑thirds.

The rise is even more pronounced in countries with significant and expanding space cooling needs. By 2050, ownership of air conditioners in India is estimated to increase tenfold, leading to a sixfold jump in peak electricity demand in buildings. This increase could be cut in half with widespread adoption of more efficient building designs and tougher minimum energy performance standards for appliances, as envisioned by the IEA's Announced Pledges Scenario , which sees countries meeting national energy and climate targets in full and on time. In India, for example, these measures are projected to more than halve the contribution to peak demand from cooling and related stress on electricity networks.

Peak electricity demand in buildings in selected regions and countries and contributions by end-use, 2022-2050

Peak electricity demand in buildings in india and indonesia and contributions by end-use, 2022-2050.

At the same time, the deployment of wind and solar PV is accelerating globally as countries look to boost energy security and decarbonise their energy systems, making electricity supply much more weather-dependent. System-level surpluses and periods of lower generation are set to become more frequent due to daily and seasonal variations in renewable energy generation. Greater flexibility will be essential to manage these fluctuations.

Taken together, these developments will require major shifts in the way power systems are operated. For energy systems to function smoothly and efficiently, total energy demand from buildings will need to be reduced, while mechanisms for adjusting electricity demand throughout a day or season will become necessary to better match renewable generation patterns.

Buildings can provide more flexibility for the energy system

Buildings themselves can also be part of the solution. They can host various distributed energy resources , such as on-site renewable energy generation and storage, smart charging for electric cars, and other connected devices. And they can use energy flexibly if they are enabled to receive signals from the grid and can adjust their energy demand accordingly.

To realise this potential, buildings need to become both more efficient and more interactive with the grid . Energy efficiency should come first, reducing overall energy demand through high-performing building envelopes and efficient equipment. Next, buildings can be equipped with solar PV systems to produce renewable electricity and energy storage so they can retain excess supply until it is needed. Then, to facilitate interaction with grids, smart sensors, controls, intelligent analytics and other digital solutions can be integrated with building energy management systems or directly with the equipment.

Consumers stand to benefit from greater flexibility. By taking advantage of time-of-use electricity tariffs , for example, they can shift energy use to off-peak times when electricity is cheaper – flexibly operating electric vehicle chargers, water heaters and other appliances in line with the needs of the grid and price signals. As greater volumes of solar PV are incorporated into the grid, this might mean using more power during daytime hours. Such demand response measures can reduce household electricity bills by 7% to 12% by 2050 in advanced economies, and by almost 20% in emerging market and developing economies, according to IEA analysis .

Electricity bill savings from demand response for households in the NZE Scenario, 2030 and 2050

Electricity bill savings from demand response for households by end-use in the nze scenario, 2030 and 2050, to deliver benefits, buildings and grids must speak the same language.

Interoperability is key to ensure that grids and buildings can communicate with each other effectively. To support this dialogue, appliances can be equipped with special devices that can respond automatically to signals from the grid. By 2030, the number of smart meters and other connected devices with automated controls and sensors in buildings is estimated to almost double from current levels.

There are signs these technologies are starting to become more widespread. The United Kingdom has developed standards for smart communications interface s for appliances that can receive instructions related to energy use from other connected devices across networks. Australia has introduced a demand response enabling device , an interface for adjusting the energy usage of appliances based on signals from the grid.

Special certifications, like the EcoPort mark , indicate that a certified device is equipped with a dedicated control module capable of communicating with the grid. The US states of Washington, Oregon and Colorado now require new electric water heaters to be equipped with such an interface so they can participate in demand response programmes initiated by utilities. Australia and New Zealand , meanwhile, now mandate that energy labels for certain types of air conditioners include information on their demand response capability.

At the building level, energy management and automation systems can also provide supervisory control of smart appliances, smart chargers for electric vehicles, on-site solar electricity generation and storage. Open communication protocols – or universally accessible rules and standards that govern how different devices and systems exchange information – can help establish interoperability and automated control, helping to manage the voltage and quality fluctuations that can be triggered by the integration of distributed energy resources.

Buildings and grids are interacting, but there are far greater possibilities

Greater interaction between buildings and grids could result in meaningful reductions in energy demand, carbon dioxide (CO 2 ) emissions and power system costs. In the United States , a government analysis found that widely adopting efficient, grid-interactive buildings nationally could cut energy demand by 116 gigawatts (GW) during peak hours – equivalent to the output of more than 200 large power plants. It would also reduce CO 2 emissions by 80 million tonnes per year by 2030 and save power systems between USD 100 billion and USD 200 billion over the next two decades.

While countries around the world are exploring opportunities to bolster interactions between buildings and grids, progress so far has been limited on the whole to relatively small-scale projects and programmes.

A demonstration project in an apartment block in Scotland in 2020 and 2021 harnessed flexibility to deliver CO 2 emissions reductions by interrupting space heating across participating households for five- to 10-minute intervals. Participants did not report any impact to their thermal comfort. In a smart neighbourhood in the US state of Alabama , a local microgrid communicates with heating and air conditioning systems in efficient homes to determine the optimised way to use, generate and store solar-generated electricity. The combination of greater efficiency and this flexibility has resulted in energy savings of 35% to 45% compared with similar homes that do not have this capacity.

There are also opportunities for grid operators to communicate not only with individual devices, but also with smart aggregators such as virtual power plants , which can enhance grid stability by dynamically balancing electricity supply and demand, while also leveraging a diverse mix of distributed energy resources to mitigate fluctuations and optimise grid operations in real-time. A number of virtual power plants are already in operation, with several in Southeast Asia (including in Malaysia , the Philippines , Singapore , Thailand and Viet Nam ).

Furthermore, new buildings can be designed in ways that prepare them to interact more closely with grids in future. Building regulations could include mandatory requirements for sufficient space and adequate pre-wiring to accommodate installations of heat pumps, electric vehicle charging stations, solar PV systems and battery storage, such as in California’s 2022 Energy Code .

Bringing efficiency and flexibility into policy making is essential

Unlocking efficiency and flexibility in buildings to support the energy systems of the future is not an easy task. Effectively developing and implementing the right packages of policies is crucial – and incorporating energy efficiency requirements, flexibility considerations and demand-response features into building and appliance regulations is key to fostering the adoption of efficient, grid-interactive buildings.

It is also essential to enact policy provisions that support the integration of smart sensors and controls into building energy management and automation systems. Requiring manufacturers to enable appliances to participate in demand response, like in Washington State , or mandating that equipment installed in new buildings use open communication protocols, such as in California , are just two examples.

To support this process, the IEA has developed an analytical framework to assess a country’s building sector and provide recommendations to accelerate the adoption of policy- and technology-related solutions for efficient grid-interactive buildings. The IEA’s initiative on Digital Demand-Driven Electricity Networks ( 3DEN ) also provides policy advice on how digital tools can support power system decarbonisation and modernisation. 

The 3DEN report Unlocking Smart Grid Opportunities in Emerging Markets and Developing Economies offers guidance for energy policy makers on ways to enable and drive investments in smart and resilient electricity grids. And an upcoming report, Managing the Seasonal Variability of Electricity Demand and Supply , will offer tools and strategies for managing both demand- and supply-side variability, taking into account weather-related impacts on system operations and flexibility needs.

Subscription successful

Thank you for subscribing. You can unsubscribe at any time by clicking the link at the bottom of any IEA newsletter.

Digital rights and responsibility in education: A scoping review

• Norma Torres-Hernández University of Jaén

Studies on digital rights in education have both gained attention and provided a framework for research, policy and practice in educational research within the field of educational technology. The potential benefits we appreciate in Internet use are inseparable from the maximum risks involved. Faced with this responsibility, individuals demand that their rights and freedoms be guaranteed in the digital environment according to their various roles as students, teachers, families or staff. This scoping review selects and analyses 54 theoretical and empirical studies from the last decade (2013-2023), identifying the main topics investigated as privacy protection in online environments, right to digital security or cybersecurity, and right to digital education. The review underscores the need to guide efforts towards digital education for citizens because the legal regulation of rights and responsibilities is necessary but insufficient. The paper also makes arguments about acceptance, limitations and implications for teacher training.

Author Biographies

María-jesús gallego-arrufat, universidad de granada.

Full professor of educational technology, University of Granada, Spain. PhD in education. She is currently leading several projects on digital education, educational actions for digital citizenship, digital rights in education and digital competences of teachers in security. She also publishes on computer-supported learning, communities of inquiry, and blended and virtual learning in higher education. 

Inmaculada García-Martínez, Universidad de Granada

Assistant lecturer at the University of Granada (Spain). She has a PhD in education. She is currently working on professional identity and psychosocial factors related with teachers and professional development. She also investigated abourt educational technology and inclusive education. She has published several scientific articles on pedagogical leadership, school organization, educational technology and emotional intelligence. She is a member of the Ibero-American Network for the Development of Professional Teaching Identity. She has participated in several research projects funded by the Spanish Ministry of Education.

María-Asunción Romero-López, Universidad de Granada

Senior lecturer, University of Granada (Spain). PhD in education. Currently works on teachers and professional development, active methodologies and educational technology, has published several scientific articles on pedagogical leadership, educational technology and active methodologies, and has participated in several research projects funded by the Spanish Ministry of Education.

Norma Torres-Hernández, University of Jaén

Professor at the University of Jaén (Spain). PhD in education. Studies in communication, education and pedagogy. She publishes and researches digital competences in initial teacher training and data protection. Other research interests are: educational technology, curriculum, teacher training and formative assessment. She is currently involved in research projects on safe and responsible use of the Internet and digital rights.

How to Cite

• Endnote/Zotero/Mendeley (RIS)

Copyright (c) 2024 María-Jesús Gallego-Arrufat, Inmaculada García-Martínez, María-Asunción Romero-López, Norma Torres-Hernández

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License .

Most read articles by the same author(s)

• Javier Calvo de Mora, María-Jesús Gallego-Arrufat, Francisco-J. Lamas, Pedro-Antonio García-López, Students’ acceptance of university institutions , Education Policy Analysis Archives: Vol. 23 (2015)
• Miguel Angel Díaz-Delgado, Inmaculada Garcia-Martinez, Standards for school principals in Mexico and Spain: A comparative study , Education Policy Analysis Archives: Vol. 27 (2019)

Education Policy Analysis Archives/Archivos Analíticos de Políticas Educativas/Arquivos Analíticos de Políticas Educativas (EPAA/AAPE;  ISSN 1068-2341 ) is a peer-reviewed, open-access, international, multilingual, and multidisciplinary journal designed for researchers, practitioners, policy makers, and development analysts concerned with education policies.

• Português (Brasil)
• Español (España)

Make a Gift

Submit a manuscript or revision, recent special issues.

Youth and Adult Education, Literacies and Decoloniality

Global Policy Mobilities in Federal Education Systems

Teacher Subjectivities in Latin America

• Data library

2024 Housing Market Forecast and Predictions: Housing Affordability Finally Begins to Turnaround

As we look ahead to 2024 , we see a mix of continuity and change in both the housing market and economy. Against a backdrop of modest economic growth, slightly higher unemployment, and easing inflation longer term interest rates including mortgage rates begin a slow retreat. The shift from climbing to falling mortgage rates improves housing affordability, but saps some of the urgency home shoppers had previously sensed. Less frenzied housing demand and plenty of rental home options keep home sales relatively stable at low levels in 2024, helping home prices to adjust slightly lower even as the number of for-sale homes continues to dwindle. 

Realtor.com ® 2024 Forecast for Key Housing Indicators

Home Prices Dip, Improving Affordability

Home prices grew at a double-digit annual clip for the better part of two years spanning the second half of 2020 through 2022, a notable burst following a growing streak that spanned back to 2012. As mortgage rates climbed, home price growth flatlined, actually declining on an annual basis in early 2023 before an early-year dip in mortgage rates spurred enough buyer demand to reignite competition for still-limited inventory. Home prices began to climb again, and while they did not reach a new monthly peak, on average for the year we expect that the 2023 median home price will slightly exceed the 2022 annual median.

Nevertheless, even during the brief period when prices eased, using a mortgage to buy a home remained expensive. Since May 2022, purchasing the typical for-sale home listing at the prevailing rate for a 30-year fixed-rate mortgage with a 20% down payment meant forking over a quarter or more of the typical household paycheck. In fact, in October 2023, it required 39% of the typical household income and this share is expected to average 36.7% for the full calendar year in 2023. This figure has typically ranged around 21%, so it is well above historical average. We expect that the return to pricing in line with financing costs will begin in 2024, and home prices, mortgage rates, and income growth will each contribute to the improvement. Home prices are expected to ease slightly, dropping less than 2% for the year on average. Combined with lower mortgage rates and income growth this will improve the home purchase mortgage payment share relative to median income to an average 34.9% in 2024, with the share slipping under 30% by the end of the year.

Home Sales Barely Budge Above 2023’s Likely Record Low

After soaring during the pandemic, existing home sales were weighed down in the latter half of 2022 as mortgage rates took off, climbing from just over 3% at the start of the year to a peak of more than 7% in the fourth quarter. The reprieve in mortgage rates in early 2023, when they dipped to around 6%, brought some life to home sales, but the renewed climb of mortgage rates has again exerted significant pressure on home sales that is exacerbated by the fact that a greater than usual number of households bought homes over the past few years, and despite stories of pandemic purchase regret , for the most part, these homeowners continue to be happy in their homes. 

This is consistent with what visitors to Realtor.com report when asked why they are not planning to sell their homes. The number one reason homeowners aren’t trying to sell is that they just don’t need to; concern about losing an existing low-rate mortgage is the top financial concern cited. Our current projection is for 2023 home sales to tally just over 4 million, a dip of 19% over the 2022 5 million total. 

With many of the same forces at play heading into 2024, the housing chill will continue, with sales expected to remain essentially unchanged at just over 4 million. Although mortgage rates are expected to ease throughout the course of the year, the continuation of high costs will mean that existing homeowners will have a very high threshold for deciding to move, with many likely choosing to stay in place.  Moves of necessity–for job changes, family situation changes, and downsizing to a more affordable market–are likely to drive home sales in 2024. 

Shoppers Find Even Fewer Existing Homes For Sale

Even before the pandemic, housing inventory was on a long, slow downward trajectory. Insufficient building meant that the supply of houses did not keep up with household formation and left little slack in the housing market. Both homeowner and rental vacancy remain below historic averages . In contrast with the existing home market, which remains sluggish, builders have been catching up, with construction remaining near pre-pandemic highs for single-family and hitting record levels for multi-family . 

Despite this, the lack of excess capacity in housing has been painfully obvious in the for-sale home market. The number of existing homes on the market has dwindled. With home sales activity to continue at a relatively low pace, the number of unsold homes on the market is also expected to remain low.  Although mortgage rates are expected to begin to ease, they are expected to exceed 6.5% for the calendar year. This means that the lock-in effect, in which the gap between market mortgage rates and the mortgage rates existing homeowners enjoy on their outstanding mortgage, will remain a factor. Roughly two-thirds of outstanding mortgages have a rate under 4% and more than 90% have a rate less than 6%.

Rental Supply Outpaces Demand to Drive Mild Further Decline in Rents

After almost a full year of double-digit rent growth between mid-2021 and mid-2022, the rental market has finally cooled down, as evidenced by the year-over-year decline that started in May 2023 . In 2024, we expect the rental market will closely resemble the dynamics witnessed in 2023, as the tug of war between supply and demand results in a mild annual decline of -0.2% in the median asking rent.

New multi-family supply will continue to be a key element shaping the 2024 rental market.  In the third quarter of 2023, the annual pace of newly completed multi-family homes stood at 385,000 units. Although absorption rates remained elevated in the second quarter, especially at lower price points, the rental vacancy rate ticked up to 6.6% in the third quarter. This uptick in rental vacancy suggests the recent supply has outpaced demand, but context is important. After recent gains, the rental vacancy rate is on par with its level right before the onset of the pandemic in early 2020, still below its 7.2% average from the 2013 to 2019 period.  Looking ahead, the strong construction pipeline– which hit a record high for units under construction this summer –is expected to continue fueling rental supply growth in 2024 pushing rental vacancy back toward its long-run average. 

While the surge in new multi-family supply gives renters options, the sheer number of renters will minimize the potential price impact. The median asking rent in 2024 is expected to drop only slightly below its 2023 level. Renting is expected to continue to be a more budget friendly option than buying in the vast majority of markets, even though home prices and mortgage rates are both expected to dip, helping pull the purchase market down slightly from record unaffordability. 

Young adult renters who lack the benefit of historically high home equity to tap into for a home purchase will continue to find the housing market challenging. Specifically, as many Millennials age past first-time home buying age and more Gen Z approach these years, the current housing landscape is likely to keep these households in the rental market for a longer period as they work to save up more money for the growing down payment needed to buy a first home. This trend is expected to sustain robust demand for rental properties. Consequently, we anticipate that rental markets favored by young adults , a list which includes a mix of affordable areas and tech-heavy job markets in the South, Midwest, and West, will be rental markets to watch in 2024.

Key Wildcards:

• Wildcard 1: Mortgage Rates With both mortgage rates and home prices expected to turn the corner in 2024, record high unaffordability will become a thing of the past, though as noted above, the return to normal won’t be accomplished within the year. This prediction hinges on the expectation that inflation will continue to subside, enabling the recent declines in longer-term interest rates to continue. If inflation were to instead see a surprise resurgence, this aspect of the forecast would change, and home sales could slip lower instead of steadying.
• Wildcard 2: Geopolitics In our forecast for 2023 , we cited the risk of geopolitical instability on trade and energy costs as something to watch. In addition to Russia’s ongoing war in Ukraine, instability in the Middle East has not only had a catastrophic human toll, both conflicts have the potential to impact the economic outlook in ways that cannot be fully anticipated. 
• Wildcard 3: Domestic Politics: 2024 Elections In 2020, amid the upheaval of pandemic-era adaptations, many Americans were on the move. We noted that Realtor.com traffic patterns indicated that home shoppers in very traditionally ‘blue’ or Democratic areas were tending to look for homes in markets where voters have more typically voted ‘red’ or Republican. While consumers also reported preferring to live in locations where their political views align with the majority , few actually reported wanting to move for this reason alone. 

Housing Perspectives:

What will the market be like for homebuyers, especially first-time homebuyers.

First-time homebuyers will continue to face a challenging housing market in 2024, but there are some green shoots. The record-high share of income required to purchase the median priced home is expected to begin to decline as mortgage rates ease, home prices soften, and incomes grow. In 2023 we expect that for the year as a whole, the monthly cost of financing the typical for-sale home will average more than $2,240, a nearly 20% increase over the mortgage payment in 2022, and roughly double the typical payment for buyers in 2020. This amounted to a whopping nearly 37% of the typical household income. In 2024 as modest price declines take hold and mortgage rates dip, the typical purchase cost is expected to slip just under $2,200 which would amount to nearly 35% of income. While far higher than historically average, this is a significant first step in a buyer-friendly direction.

How can homebuyers prepare? 

Homebuyers can prepare for this year’s housing market by getting financially ready. Buyers can use a home affordability calculator , like this one at Realtor.com to translate their income and savings into a home price range. And shoppers can pressure test the results by using a mortgage calculator to consider different down payment, price, and loan scenarios to see how their monthly costs would be impacted. Working with a lender can help potential buyers explore different loan products such as FHA or VA loans that may offer lower mortgage interest rates or more flexible credit criteria. 

Although prices are anticipated to fall in 2024, housing costs remain high, and a down payment can be a big obstacle for buyers. Recent research shows that the typical down payment on a home reached a record high of $30,000 .  To make it easier to cobble together a down payment, shoppers can access information about down payment assistance options at Realtor.com/fairhousing and in the monthly payment section of home listing pages. Furthermore, home shoppers can explore loan products geared toward helping families access homeownership by enabling down payments as low as 3.5% in the case of FHA loans and 0% in the case of VA loans .

What will the market be like for home sellers?

Home sellers are likely to face more competition from builders than from other sellers in 2024. Because builders are continuing to maintain supply and increasingly adapting to market conditions, they are increasingly focused on lower-priced homes and willing to make price adjustments when needed. As a result, potential sellers will want to consider the landscape for new construction housing in their markets and any implications for pricing and marketing before listing their home for sale.

What will the market be like for renters?

In 2024, renting is expected to continue to be a more cost-effective option than buying in the short term even though we anticipate the advantage for renting to diminish as home prices and mortgage rates decline. 

However, for those considering the pursuit of long-term equity through homeownership, it’s essential to not only stay alert about market trends but also to carefully consider the intended duration of residence in their next home. When home prices rise rapidly, like they did during the pandemic, the higher cost of purchasing a home may break even with the cost of renting in as little as 3 years. Generally, it takes longer to reach the breakeven point, typically within a 5 to 7-year timeframe. Importantly, when home prices are falling and rents are also declining, as is expected to be the case in 2024, it can take longer to recoup some of the higher costs of buying a home. Individuals using Realtor.com’s Rent vs. Buy Calculator can thoroughly evaluate the costs and benefits associated with renting versus buying over time and how many years current market trends suggest it will take before buying is the better financial decision. This comprehensive tool can provide insights tailored to a household’s specific rent versus buying decision and empowers consumers to consider not only the optimal choice for the current month but also how the trade-offs evolve over several years.

Local Market Predictions:

All real estate is local and while the national trends are instructive, what matters most is what’s expected in your local market. 

Sign up for updates

Join our mailing list to receive the latest data and research.

Demand Analysis with Many Prices

From its inception, demand estimation has faced the problem of "many prices." This paper provides estimators of average demand and associated bounds on exact consumer surplus when there are many prices in cross-section or panel data. For cross-section data we provide a debiased machine learner of consumer surplus bounds that allows for general heterogeneity and solves the "zeros problem" of demand. For panel data we provide bias corrected, ridge regularized estimators of average coefficients and consumer surplus bounds. In scanner data we find smaller panel elasticities than cross-section and that soda price increases are regressive.

Research for this paper was supported by NSF Grant 1757140. Helpful comments were provided by R. Blundell, B. Deaner, Y. Gao, M. Harding, S. Hoderlein, M. Keene, and J. Shapiro. B. Deaner, Y Gao, M. Hardy, and K. Quist provided excellent research assistance. The empirical work here is researchers own analyses based in part on data from The Nielsen Company (US), LLC and marketing databases provided through the Nielsen Datasets at the Kilts Center for Marketing Data Center at The University of Chicago Booth School of Business. The conclusions drawn from the Nielsen data are those of the researchers and do not reflect the views of Nielsen, nor of the National Bureau of Economic Research. Nielsen is not responsible for, had no role in, and was not involved in analyzing and preparing the results reported herein.

Research for this paper was supported by NSF Grant 1757140. No other support to disclose.

MARC RIS BibTeΧ

Download Citation Data

More from NBER

In addition to working papers , the NBER disseminates affiliates’ latest findings through a range of free periodicals — the NBER Reporter , the NBER Digest , the Bulletin on Retirement and Disability , the Bulletin on Health , and the Bulletin on Entrepreneurship  — as well as online conference reports , video lectures , and interviews .