empirical research and forecasting institute

SI 2023 Forecasting & Empirical Methods

Supported by the national science foundation grant #1757139.

conference schedule

Participants

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 .

Forecasting nonstationary time series based on Hilbert-Huang transform and machine learning

• Data Analysis
• Published: 11 May 2014
• Volume 75 , pages 922–934, ( 2014 )

Cite this article

• V. G. Kurbatsky 1 ,
• D. N. Sidorov 1 ,
• V. A. Spiryaev 1 &
• N. V. Tomin 1  

345 Accesses

16 Citations

Explore all metrics

We propose a modification of the adaptive approach to time series forecasting. On the first stage, the original signal is decomposed with respect to a special empirical adaptive orthogonal basis, and the Hilbert’s integral transform is applied. On the second stage, the resulting orthogonal functions and their instantaneous amplitudes are used as input variables for the machine learning unit that employs a hybrid genetic algorithm to train an artificial neural network and a regressive model based on support vector machines. The efficiency of the proposed approach is demonstrated on real data coming from Nord Pool Spot and Australian National Energy Market.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Forecasting by Using the Optimal Time Series Method

Time series forecasting based on wavelet decomposition and feature extraction, koopman operator framework for time series modeling and analysis.

Brockwell, P.J. and Davis, R.A., Introduction to Time Series and Forecasting , Springer Texts in Statistics, New York: Springer-Verlag, 2002.

Book   MATH   Google Scholar  

Fan, J. and Yao, Q., Nonlinear Time Series: Nonparametric and Parametric Methods , New York: Springer-Verlag, 2003.

Book   Google Scholar  

Khaikin, S., Neironnye seti (Neural Networks), Moscow: Wil’yams, 2006.

Google Scholar  

Osovskii, S., Neironnye seti dlya obrabotki informatsii (Neural Networks for Information Processing), Moscow: Finansy i Statistika, 2004.

Zhang, G.P., Patuwo, B.E., and Hu, M.Y., Forecasting with Artificial Neural Networks: The State of the Art, Int. J. Forecast. , 1998, vol. 14, no. 5, pp. 35–62.

Article   Google Scholar  

Breiman, H., Random Forests, J. Machine Learning , 2001, vol. 45, pp. 5–32.

Article   MATH   Google Scholar  

Areekul, P., Senjyu, T., Toyama, H., and Yona, A., A Hybrid ARIMA and Neural Network Model for Short-Term Price Forecasting in Deregulated Market, IEEE Trans. Power Syst. , 2010, vol. 25, no. 1, pp. 524–530.

Adya, M. and Collopy, F., How Effective are Neural Networks at Forecasting and Prediction? A Review and Evaluation, Int. J. Forecast. , 1998, vol. 17, nos. 5–6, pp. 481–495.

Callen, L.J., Kwan, C.C., Yip, C.P., and Yuan, Y., Neural Network Forecasting of Quarterly Accounting Earnings, Int. J. Forecast. , 1996, vol. 12, no. 4, pp. 475–482.

Heravi, S., Osborn, D.R., and Birchenhall, C.R., Linear Versus Neural Network Forecasts for European Industrial Production Series, Int. J. Forecast. , 2004, vol. 20, no. 3, pp. 435–446.

Yan, W., Toward Automatic Time-Series Forecasting Using Neural Networks, IEEE Trans. Neural Networks Learning Syst. , 2012, vol. 23, no. 7, pp. 1028–1039.

Vapnik, V.N. and Lerner, A.Ya., Pattern Recognition Using Generalized Portraits, Autom. Remote Control , 1963, vol. 24, no. 6, pp. 709–715.

Vapnik, V.N., Vosstanovlenie zavisimostei po empiricheskim dannym (Reconstructing Dependencies by Empirical Data), Moscow: Nauka, 1979.

Vapnik, V.N. and Chervonenkis, A.Ya., Teoriya raspoznavaniya obrazov (Pattern Recognition Theory), Moscow: Nauka, 1974.

MATH   Google Scholar  

Vasil’ev, I.L. and Sidorov, D.N., An Application of Cluster Analysis to Automated Defect Recognition, Probl. Upravlen. , 2007, no. 4, pp. 36–42.

Cover, T., Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition, IEEE Trans. Electron. Comput. , 1965, vol. 14, pp. 326–334.

Huang, N.E., Zheng, S., Long, S.R., et al., The Empirical Mode Decomposition and the Hilbert Spectrum for Non-Linear and Non-Stationary Time Series Analysis, Proc. Royal Soc. London, Ser. A: Math., Phys. Eng. Sci. , 1971, vol. 454, pp. 903–995.

Article   MathSciNet   Google Scholar  

Gorban’, A.N., Dunin-Barkovskii, V.L., and Mirkes, E.M., Neiroinformatika (Neuroinformatics), Novosibirsk: Nauka, 1998.

Gerikh, V.P., Kolosok, I.N., Kurbatsky, V.G., and Tomin, N.V., Application of Neural Network Technologies for Price Forecasting in the Liberalized Electricity Market, Power Electr. Eng., Sci. J. Riga Techn. Univ. , 2009, no. 5, pp. 91–96.

Friedman, J.H., Stochastic Gradient Boosting, Comput. Statist. Data Anal. , 2002, vol. 38, pp. 367–378.

Article   MATH   MathSciNet   Google Scholar  

Yun, Z., RBF Neural Network and ANFIS-Based Short-Term Load Forecasting Approach in Real-Time Price Environment, IEEE Trans. Power Syst. , 2008, vol. 23, no. 3, pp. 853–858.

Neironnye seti. STATISTICA Neural Networks: Metodologiya i tekhnologii sovremennogo analiza dannykh (Neural Networks. STATISTICA Neural Networks: Methodology and Technology of Modern Data Mining), Borovikov, V.P., Ed., Moscow: Goryachaya Liniya-Telekom, 2008.

Zhu, C., Byrd, C.V., Lu, P., and Nocedal, J., Algorithm 778: L-BFGS-B, Fortran Subroutines for Large Scale Bound Constrained Optimization, ACM Trans. Math. Softw. , 1997, vol. 23, no. 4, pp. 550–560.

Aizerman, M.A., Braverman, E.M., and Rozonoer, L.I., Metod potentsial’nykh funktsii v teorii obucheniya mashin (Method of Potential Functions in Machine Learning Theory), Moscow: Nauka, 1970.

Tikhonov, A.N. and Arsenin, V.Ya., Metody resheniya nekorrektnykh zadach (Methods for Solving Ill-Posed Problems), Moscow: Nauka, 1979.

Morozov, V.A., Methods for Solving Incorrectly Posed Problems , New York: Springer, 1984.

Nesterov, Yu.E., Vvedenie v vypukluyu optimizatsiyu (Introduction to Convex Optimization), Polyak, B. and Nazin, S., Eds., Moscow: Mosk. Tsentr Nepreryvn. Mat. Obrazov., 2010.

Hornik, K., Stinchcombe, M., and White, H., Multilayer Feedforward Networks are Universal Approximators, Neural Networks , 1989, vol. 2, pp. 359–366.

Flandrin, P., Rilling, G., and Goncalves, P., On Empirical Mode Decomposition and Its Algorithms, IEEE Signal Proc. Lett. , 2004, vol. 11, no. 2, pp. 112–114.

Czerny, V., Thermodynamical Approach to the Traveling Salesman Problem: An Efficient Simulation Algorithm, J. Optim. Theory Appl. , 1985, vol. 45, pp. 41–51.

Shumkov, D.S., Development and Study of Forecasting Methods Based on SVM Models, Cand. Sci. (Tech.) Dissertation , St. Petersburg: State Univ. of Information Technologies, Mechanics, and Optics, 2009.

Kurbatsky, V.G. and Tomin, N.V., Using PVK “ANAPRO” for Analysis and Forecasting of Mode Parameters and Technological Characteristics in Electical Energy Systems, in Tr. XIII Baikal. Vseross. Konf. “Informatsionnye i matematicheskie tekhnologii v nauke i upravlenii” (Proc. XIII Baikal All-Russian Conf. “Informational and Mathematical Technologies in Science and Management”), Irkutsk: Inst. Sist. Energet. Sib. Otd. Ross. Akad. Nauk, 2008, part I.

Andreev, A.V., Livshits, G.N., Mashanskii, A.M., et al., A Hierarchical System for Automated Control over Frequency and Overflows in Active Power of EES Russia, Elektrich. Stantsii , 2010, no. 3, pp. 43–51.

Kalman, R.E. and Bucy, R.S., New Results in Linear Filtering and Prediction Theory, Trans. ASME, Ser. D, J. Basic Eng. , 1961, vol. 83, pp. 95–108.

Download references

Author information

Authors and affiliations.

Melentiev Energy Systems Institute, Siberian Branch, Russian Academy of Sciences, Irkutsk, Russia

V. G. Kurbatsky, D. N. Sidorov, V. A. Spiryaev & N. V. Tomin

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to V. G. Kurbatsky .

Additional information

Original Russian Text © V.G. Kurbatsky, D.N. Sidorov, V.A. Spiryaev, N.V. Tomin, 2014, published in Avtomatika i Telemekhanika, 2014, No. 5, pp. 143–158.

Rights and permissions

Reprints and permissions

About this article

Kurbatsky, V.G., Sidorov, D.N., Spiryaev, V.A. et al. Forecasting nonstationary time series based on Hilbert-Huang transform and machine learning. Autom Remote Control 75 , 922–934 (2014). https://doi.org/10.1134/S0005117914050105

Download citation

Received : 04 April 2012

Published : 11 May 2014

Issue Date : May 2014

DOI : https://doi.org/10.1134/S0005117914050105

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

• Support Vector Machine
• Remote Control
• Empirical Mode Decomposition
• Support Vector Machine Model
• Original Time Series
• Find a journal
• Publish with us
• Track your research

INSTITUTE OF ECONOMICS

Russian academy of sciences.

• Research Units
• Administration
• The 90th Anniversary
• Research fields
• International Agreements
• Our Partners
• Scientific News
• Forthcoming Events
• Media About Us
• Working Papers

OUR JOURNALS

Bulletin of the IE RAS

The Journal of the New Economic Association

Society and Economy

Voprosy Teoreticheskoy Ekonomiki

World of Transformations

Administrative office

Phone: +7 (499) 124-74-80 Fax:    +7  (499) 724-14-09

[email protected]

32 Nakhimovskiy Prospekt, Moscow, Russia 117218

Any use of information and materials posted on the site is allowed only if there is a hyperlink to the site of IE RAS. When citing publications posted on the site, a hyperlink to the source is required.

• Contact information

The Experience

• Career Impact
• Inclusion and Belonging
• Global Opportunities

More about Kellogg

• History & Legacy
• Convocation Ceremony

Degree Programs

• Full-Time MBA
• Executive MBA
• Master in Management
• Evening & Weekend MBA
• Certificate Program for Undergraduates
• Which Program is Right for Me?
• Academic Calendars

Executive Education

• Online Programs
• Programs for Individuals
• Nonprofit Programs
• Programs for Groups
• The Kellogg Advantage
• Contact Executive Education
• Request a Brochure
• Find a Program
• Alumni Network
• Career Journeys
• Global Impact
• Student Stories
• Applying to Kellogg

Publications and blogs

• Kellogg Magazine
• Kellogg Insight
• See All News + Stories

Academics + Research

• Faculty Directory
• Research Centers
• Case Studies
• Faculty Teaching Awards
• Academic Departments
• Research + Books
• Faculty Recruiting

Academic expertise

• Data Analytics
• Family Business
• Leadership & Organizations
• Social Impact
• Entrepreneurship
• Full-Time MBA Admissions
• Evening & Weekend MBA Admissions
• Executive MBA Admissions

Additional resources

• Master in Management Admissions
• PhD / Doctoral Admissions
• Undergraduate Certificate Admissions
• Admissions Events
• Financial Aid Office
• Log into my account portal
• Companies + Recruiters

Kellogg creates first research institute applying complexity sciences to unlock new understandings of societal, market and business issues

• Kellogg News

Northwestern University’s Kellogg School of Management announced today the creation of the Ryan Institute on Complexity to be led by distinguished faculty in the areas of physics, economics and sociology. The Ryan Institute will comprise a revolutionary research lab designed to change the way business, markets and societal issues are studied, combining multidisciplinary talents and quantitative sciences in new ways to tackle bigger problems faster.   Funded by a $25 million gift from the Ryan Family Foundation, the Ryan Institute will place Kellogg and Northwestern at the forefront of solving increasingly complex societal, business and market challenges by harnessing the power of big data and artificial intelligence. The institute will provide Kellogg students with an understanding of powerful new quantitative approaches to problem solving.     The field of complexity science had a watershed moment in 2021 when the Nobel Prize in Physics was awarded in this area for the first time. But complexity science’s potential in the realm of business is just starting to be tapped, and the possibilities are vast — in better understanding everything from the intertwined forces driving a nation’s innovativeness to the inner workings of a global team dynamic. The goal is to improve understanding of how the success of organizations, regions and nations build from their deep and rich interconnections. With this focus, the Ryan Institute will be the first of its kind to be housed in a business school. It will gather leaders from academia and industry in diverse fields, along with PhD students and postdoctoral fellows to collectively study the future of quantitative sciences, complex systems and the complex issues affecting businesses and society. Initial areas of focus include the power of social networks, the secrets of invention and human-machine partnerships.  Unique to the institute will be a “dry lab” setting typically found in the hard sciences, which will enable scholars to work with big data and the quantitative tools needed to study social and business phenomena on a large scale. This approach holds the promise of generating deeper and more generalizable insights into society’s biggest questions, such as understanding human-machine partnerships at the forefront of generative AI. A key pillar of study will focus on leveraging large language models (LLMs) with the belief that generative AI will not replace humans, but those who understand AI will replace those who don’t. Given the explosion of big data and the rapid acceleration of AI, there are now opportunities to better understand the world in ways that previously were subject only to hypothesis.        “Kellogg has always taken an interdisciplinary approach to open new areas,” said Kellogg Dean Francesca Cornelli. “Our vision is bold — that complexity science shall permeate every aspect of business, with the most effective leaders succeeding through understanding and managing a system’s connectivity. Thanks to the generosity of the Ryan Family, Kellogg will drive a new field and best prepare the leaders of the future.”  “We are thrilled to support the establishment of this revolutionary research institute that will place Kellogg and Northwestern University at the forefront of the study of complexity science,” said Pat Ryan, Jr (’97 JD, MBA) of the Ryan Family Foundation. “Cutting-edge analytical approaches can now unlock previously unimaginable understandings of our complex world that will be transformational for business and society.” 

The Ryan Institute will be led by three Kellogg professors who are all highly recognized leaders in their fields, as well as frequent collaborators: Dashun Wang , a physicist and Professor of Management and Organizations; Ben Jones , an economist and the Gordon and Llura Gund Family Professor of Entrepreneurship and Professor of Strategy; and Brian Uzzi , a sociologist and the Richard L. Thomas Professor of Leadership and Organizational Change.  “If we can integrate complexity science and this fundamental thinking from physics and the natural sciences and apply it to business and markets, developing thought leadership and training future leaders in the school — that could be a very meaningful contribution to society,” said Wang.  Research and tools emerging from the Ryan Institute will also drive the creation of unique curriculum at Kellogg, including the first PhD training program in a business school helping to train future thought leaders in complexity. The Institute will also collaborate closely with other Northwestern schools and institutions.   The Ryan Institute will hold an annual conference as a premier, global convening of thought leaders in the study of complexity. The Ryan Institute Conference will bring together academia and industry to provide opportunities for collaboration across leaders in the field.   About the Ryan Family Foundation and Pat & Shirley Ryan family   The Ryan family [Pat '59, '09 H ('97, '00 P) and Shirley '61, '19 H ('97, '00 P); Pat '97 JD, MBA and Lydia; Rob '00 JD, MBA and Jennifer; and Corbett] has made deep and broad philanthropic investments across the institution including nanotechnology, the musical arts, the Ryan Family Scholars Program for high-achieving, low-income students with exceptional leadership potential, and the ongoing efforts to Rebuild Ryan Field. The Patrick G. and Shirley W. Ryan Family Foundation is the philanthropic arm of the Ryan family.    Patrick G. Ryan is a 1959 Northwestern graduate. He received his undergraduate degree in business from what was then called the School of Business and now is named the Kellogg School of Management. He also received an honorary degree from the University in 2009 in appreciation for his 14 years of service as chairman of Northwestern’s Board of Trustees. In 2013, he was inducted into Northwestern’s Athletics Hall of Fame.  Shirley Welsh Ryan is a 1961 Northwestern graduate. She received her undergraduate degree in English Literature from what was then called the College of Arts and Sciences and is now named the Weinberg College of Arts and Sciences. In 2019, Northwestern awarded Mrs. Ryan the honorary title of Doctor of Humane Letters.  Mr. Ryan is distinguished as one of the nation’s most successful entrepreneurs and prominent civic leaders. His first business venture while a student involved selling scrapbooks to fellow students, which paid for his Northwestern education. Mr. Ryan founded and served for 41 years as CEO of Aon Corporation, the leading global provider of risk management, insurance and reinsurance brokerage. At the time of his retirement, Aon had nearly $8 billion in annual revenue with more than 500 offices in 120 countries.   In 2010, Mr. Ryan founded Ryan Specialty, a service provider of specialty products and solutions for insurance brokers, agents and carriers. The firm provides distribution, underwriting, product development, administration and risk management services by acting as a wholesale broker and a managing underwriter.  Mr. Ryan currently serves as chairman and CEO of Ryan Specialty Holdings, Inc., which completed its initial public offering in July 2021. The firm’s shares trade on the New York Stock Exchange under the symbol “RYAN.” Mr. Ryan is distinct in having founded and built two major New York Stock Exchange traded companies.   Mr. Ryan is a member of the Chicago Business Hall of Fame, and a member and past president of the Economic Club of Chicago. He also is a member of the International Insurance Hall of Fame and the Automotive Hall of Fame, a member and past chairman of Northwestern’s Board of Trustees, a recipient of the esteemed Horatio Alger Award and a member of the American Academy of Arts and Sciences. He is a former director of numerous public multi-national corporations as well as many major cultural and not-for-profit organizations.   Shirley Welsh Ryan is founder of Pathways.org, which is used by 40 million parents and healthcare professionals annually through its video-based website and social media in every country except North Korea. Three hundred U.S. institutions of higher learning use Pathway.org’s free materials. Mrs. Ryan’s pioneering work to empower every infant’s fullest physical development has won numerous awards. Two U.S. presidents have appointed her to the National Council on Disability in Washington D.C., which advises the U.S. Congress on disability policy.  In 2017, Pathways.org merged with the Shirley Ryan Ability Lab, acclaimed for 32 years as the number one U.S. rehabilitation hospital by U.S. News and World Report.  The Pathways.org Medical Round Table (P.M.R.T.), created in 1990, is the first Infant Milestone Chart of typical and atypical development to be endorsed by the American Academy of Pediatrics (A.A.P.). All Pathways.org material is in accord with the leadership of P.M.R.T. and A.A.P.  Mrs. Ryan is a strong believer in the power of early infant detection, therapeutic intervention, universal accessibility, and the concept that all children can learn. She serves on the boards of University of Notre Dame, the Lyric Opera of Chicago, the Art Institute of Chicago, the Chicago Council on Global Affairs, Alain Locke Charter School and WTTW-PBS. She also has served on the boards of the Kennedy Center for Performing Arts in Washington D.C. and Ronald McDonald House Charities; has chaired the Chicago Community Trust; and founded the Lincoln Park Zoo Women’s Board. For 46 years, Mrs. Ryan has led a Northwestern graduate-level course entitled Learning for Life.  Mrs. Ryan has been awarded honorary doctorates from Northwestern, the University of Notre Dame and the University of Illinois at Chicago. She also has received the Chicago History Museum Award for Distinction in Civic Leadership.  In addition to earning her B.A. from Northwestern, Mrs. Ryan studied at the Sorbonne of the University of Paris and the École du Louvre in Paris.  In addition to Mr. and Mrs. Ryan, the Ryan Family includes Northwestern Trustee Pat ’97 JD, MBA and Lydia; Rob ’00 JD, MBA and Jennifer; and Corbett.