A TIME SERIES FORECASTING METHOD BASED ON COGNITIVE FUZZY MODELING AND REGRESSION ANALYSIS
Abstract
The relevance of the study stems from the low effectiveness of traditional time series forecasting methods under conditions of high uncertainty and limited data, which are typical of weakly formalized systems. The aim of the work is to develop and substantiate a time series forecasting method based on a hybrid approach that integrates cognitive fuzzy modelling, regression analysis, and the analytic network process. Within the study, a systematic review and comparative analysis of existing forecasting methods was carried out, including approaches based on fuzzy logic, neural network and cognitive modelling, as well as ensemble and hybrid methods, and their limitations were identified when dealing with small samples, nonlinear dependencies, and uncertainty. The proposed method includes: the construction of fuzzy cognitive maps, defuzzification of linguistic assessments, clustering of factors, application of the analytic network process to determine priorities, and the formation of a weighted regression model. The model undergoes statistical validation using the , , , and metrics, as well as diagnostic checks of the assumptions underlying regression analysis, including tests for multicollinearity and autocorrelation. Application of the method reduced from 0.38 to 0.22, from 0.30 to 0.18, and from 11.65 % to 7.12 %, thereby confirming an improvement in the accuracy and robustness of forecasts under limited data compared with classical multiple regression. The novelty of the proposed method lies in the integration of cognitive modelling, regression analysis, and the analytic network process, whereby the strengths of each component compensate for their individual limitations, providing more accurate and robust forecasting under the uncertainty inherent in the system under study. The practical significance of the work consists in the possibility of applying the proposed method to support decision-making and to enhance the validity of forecasts in various subject domains and situations characterized by a limited number of observations, a substantial role of expert judgments, and a complex structure of causal relationships between indicators over time
References
1. Kitova O.V., D'yakonova L.P., Kitov V.A., Savinova V.M. Primenenie neyronnykh setey dlya prognozi-rovaniya sotsial'no-ekonomicheskikh vremennykh ryadov [Application of neural networks for forecast-ing socio-economic time series], Russian Economic Bulletin, 2020, Vol. 3, No. 5, pp. 188-201.
2. Yarushev S.A., Averkin A.N., Efremova N.A. Gibridnye nechetkie kognitivnye karty v zadachakh pod-derzhki prinyatiya resheniy i prognozirovaniya [Hybrid fuzzy cognitive maps in decision support and forecasting problems], Programmnye produkty, sistemy i algoritmy [Software products, Systems and Algorithms], 2017, No. 4, pp. 18-18.
3. Dolgov Yu.A., Dolgov A.Yu., Stolyarenko Yu.A. Analiz vyborok malogo ob"ema i ikh primenenie [Anal-ysis of small samples and their application], Vestnik Pridnestrovskogo universiteta. Seriya: Fiziko-matematicheskie i tekhnicheskie nauki. Ekonomika i upravlenie [Bulletin of Pridnestrovian University. Series: Physical, Mathematical and Technical Sciences. Economics and Management], 2013, No. 3 (45), pp. 79-90. EDN XVSWBJ.
4. Vorob'ev G.G. Nechetkie kognitivnye karty v iskusstvennom intellekte [Fuzzy cognitive maps in artifi-cial intelligence], MCE.SU: «Matematika. Komp'yuter. Obrazovanie» [MCE.SU: "Mathematics. Com-puter. Education"], 2010. Available at:https://www.mce.biophys.msu.ru/archive/doc61132/ doc.pdf (ac-cessed 01 July 2025).
5. Cheng L., Yu T. A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems, International Journal of Energy Research, 2019, Vol. 43, No. 6, pp. 1928-1973.
6. Andrianova E.G., Golovin S.A., Zykov S.V., Les'ko S.A., Chukalina E.R. Obzor sovremennykh modeley i metodov analiza vremennykh ryadov dinamiki protsessov v sotsial'nykh, ekonomicheskikh i sotsiotekhnicheskikh sistemakh [Review of modern models and methods for analyzing time series of process dynamics in social, economic and sociotechnical systems], Rossiyskiy tekhnologicheskiy zhurnal [Russian Technological Journal], 2020, No. 8 (4), pp. 7-45.
7. Arutyunov A.L., Ivanyuk V.A., Tsvirkun A.D. Razrabotka instrumental'nykh sredstv prognozirovaniya v sotsial'no-ekonomicheskikh sistemakh [Development of forecasting tools in socio-economic systems], Upravlenie razvitiem krupnomasshtabnykh system [Management of large-scale systems development], 2015, pp. 241-293.
8. Ivanyuk V., Sunchalin A., Sunchalina A. Development of an intelligent ensemble forecasting system, Advances in Intelligent Systems and Computing, 2020, Vol. 1294, pp. 491-500. DOI: 10.1007/978-3-030-63322-6_40.
9. Parray I.R., Khurana S.S., Kumar M., Altalbe A.A. Time Series Data Analysis of Stock Price Movement Using Machine Learning Techniques, Soft Computing, 2020, No. 24, pp. 16509-16517. Available at: https://doi.org/10.1007/s00500-020-04957-x.
10. Alamir Kh.S., Zargaryan E.V., Zargaryan Yu.A. Model' prognozirovaniya transportnogo potoka na osnove neyronnykh setey dlya predskazaniya trafika na dorogakh [A model for predicting traffic flow based on neural networks for predicting road traffic], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2021, No. 6 (223), pp. 124-132.
11. Zelezetskiy D.V. Glubokoe obuchenie v zadache prognozirovaniya finansovykh vremennykh ryadov [Deep learning in the problem of forecasting financial time series], Tr. Moskovskogo fiziko-tekhnicheskogo institute [Transactions of the Moscow Institute of Physics and Technology], 2024, Vol. 16, No. 3 (63), pp. 35-48.
12. Sina L.B., Secco C.A., Blazevic M., Nazemi K. Hybrid Forecasting Methods—A Systematic Review, Electronics, 2023, No. 12, pp. 2019. Available at: https://doi.org/10.3390/ electronics12092019.
13. Alharbi M.H. Prediction of the Price of Advanced Global Stock Markets Using Machine Learning: Comparative Analysis, Journal of Financial Risk Management, 2024, Vol. 13, No. 4, pp. 689-702.
14. Ivanyuk V. The method of residual-based bootstrap averaging of the forecast ensemble, Financial Inno-vation, 2023, Vol. 9, No. 1, pp. 37.
15. Wu H., Levinson D. The ensemble approach to forecasting: A review and synthesis, Transportation Research Part C: Emerging Technologies, 2021, Vol. 132, pp. 103357.
16. Ke G. et al. Lightgbm: A highly efficient gradient boosting decision tree, Advances in neural information processing systems, 2017, Vol. 30.
17. Chen T., Guestrin C. Xgboost: A scalable tree boosting system, Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785-794.
18. Freund Y., Schapire R.E. A decision-theoretic generalization of on-line learning and an application to boosting, Journal of computer and system sciences, 1997, Vol. 55, No. 1, pp. 119-139.
19. Posmakov N.P., Emelyanenko A.S., Kireev V.S. Fuzzy Cognitive Map Ensembles to Solve Regression and Time Series Tasks, 2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus). IEEE, 2022, pp. 406-409.
20. Katwal S., Shrestha R., Sharma G. Analysis of Website Traffic Time Series Forecasting using ARIMA, Prophet, and LSTM RNN, International Journal of Research Publications, 2024, No. 146 (1),
pp. 316-326. doi: 10.47119/IJRP1001461420246271.
21. Wu X. et al. The development of a hybrid wavelet-ARIMA-LSTM model for precipitation amounts and drought analysis, Atmosphere, 2021, Vol. 12, No. 1, pp. 74.
22. Podgorskaya S.V. i dr. Postroenie nechetkikh kognitivnykh modeley sotsial'no-ekonomicheskikh sistem na primere modeli upravleniya kompleksnym razvitiem sel'skikh territoriy [Construction of fuzzy cogni-tive models of socio-economic systems using the example of a management model for integrated devel-opment of rural areas], Biznes-informatika [Business Informatics], 2019, Vol. 13, No. 3, pp. 7-19.
23. Kholodova M.A., Podvesovskiy A.G., Isaev R.A. Nechetkaya kognitivnaya model' strategicheskogo up-ravleniya agroprodovol'stvennym rynkom [Fuzzy cognitive model of strategic management of the agri-food market], Modeli, sistemy, seti v ekonomike, tekhnike, prirode i obshchestve [Models, Systems, Networks in Economics, Technology, Nature and Society], 2022, No. 2 (42), pp. 106-125.
24. Zakharova A.A., Podvesovskiy A.G., Isaev R.A. Nechetkie kognitivnye modeli v upravlenii slabostruktu-rirovannymi sotsial'no-ekonomicheskimi sistemami [Fuzzy cognitive models in the management of weakly structured socio-economic systems], Informatsionnye i matematicheskie tekhnologii v nauke i upravlenii [Information and Mathematical Technologies in Science and Management], 2020, No. 4 (20), pp. 5-23.
25. Zimonina Yu.V., Isaev R.A., Podvesovskiy A.G. Podsistema obmena dannymi v sostave sistemy pod-derzhki prinyatiya resheniy na osnove kognitivnogo modelirovaniya «IGLA»: arkhitektura i osobennosti realizatsii [Data exchange subsystem as part of the decision support system based on cognitive modeling "IGLA": architecture and implementation features], Fiziko-tekhnicheskaya informatika (CPT2020) [Physical and Technical Informatics (CPT2020)], 2020, pp. 12-16.
26. Romanov R.M. Postroenie i primenenie nechetkikh kognitivnykh kart dlya otsenki vliyaniya kapital'nykh proektov na finansovye rezul'taty kompanii [Construction and application of fuzzy cognitive maps for assessing the impact of capital projects on the company's financial results], Sovremennaya nauka: ak-tual'nye problemy teorii i praktiki. Seriya: Estestvennye i tekhnicheskie nauki [Modern Science: Current Problems of Theory and Practice. Series: Natural and Technical Sciences], 2025, No. 1 (2), pp. 62-67. DOI 10.37882/2223-2966.2025.01-2.17.
27. Averkin A.N., Yarushev S.A., Pavlov V.Yu. Kognitivnye gibridnye sistemy podderzhki prinyatiya resheniy i prognozirovaniya [Cognitive hybrid systems for decision support and forecasting], Programmnye produkty i sistemy [Software Products and Systems], 2017, Vol. 30, No. 4, pp. 632–642. DOI: 10.15827/0236-235X.120.632-642.
28. Avdeeva Z.K., Grebenyuk E.A., Kovriga S.V. Cognitive modelling-driven time series forecasting for predicting target indicators in non-stationary processes, IFAC-PapersOnLine, 2021, Vol. 54, No. 13, pp. 91-96.
29. Kulinich A.A. Komp'yuternye sistemy analiza situatsiy i podderzhki prinyatiya resheniy na osnove kogni-tivnykh kart: podkhody i metody [Computer systems for situation analysis and decision support based on cognitive maps: approaches and methods], Problemy upravleniya [Problems of Management], 2011, No. 4, pp. 31-45.
30. Babeshko L.O., Orlova I.V. Ekonometrika i ekonometricheskoe modelirovanie v Excel i R [Economet-rics and econometric modeling in Excel and R], 2021.
31. Handa R. Prediction of foreign exchange rate using regression techniques, 2017.
32. Yilmaz F.M., Arabaci O. Should deep learning models be in high demand, or should they simply be a very hot topic? A comprehensive study for exchange rate forecasting, Computational Economics, 2021, Vol. 57, No. 1, pp. 217-245.
33. Hadwan M. et al. A Hybrid Neural Network and Box-Jenkins Models for Time Series Forecasting, Computers, Materials & Continua, 2022, Vol. 70, No. 3.
34. Pashshoev B., Petrusevich D.A. Analiz neyrosetevykh modeley dlya prognozirovaniya vremennykh ryadov [Analysis of neural network models for time series forecasting], Russian Technological Journal [Russian Technological Journal], 2024, Vol. 12, No. 4, pp. 106-116.
35. Borisov V.V., Luferov V.S. Metod mnogomernogo analiza i prognozirovaniya sostoyaniya slozhnykh sistem i protsessov na osnove nechetkikh kognitivnykh temporal'nykh modeley [Method of multivariate analysis and forecasting of the state of complex systems and processes based on fuzzy cognitive tem-poral models], Sistemy upravleniya, svyazi i bezopasnosti [Control, Communications and Security Sys-tems], 2020, No. 2, pp. 1-23. DOI: 10.24411/2410-9916-2020-10201.
36. Borisov V.V., Fedulov A.S. «Sovmestimye» nechetkie kognitivnye karty [“Compatible” fuzzy cognitive maps], Sistemy komp'yuternoy matematiki i ikh prilozheniya [Systems of Computer Mathematics and Their Applications], 2016, No. 17, pp. 41-43.
37. Saati T.L. Prinyatie resheniy pri zavisimostyakh i obratnykh svyazyakh: analiticheskie seti [Decision making with dependencies and feedbacks: analytical networks]: trans. from Engl. by.
O.N. Andreychikovoy , scientific ed. A.V. Andreychikov, O.N. Andreychikova. 2nd ed. Moscow: LIBROKOM: URSS, 2009, 357 p. ISBN 978-5-397-00844-0.
38. Eng K., Chen Y.Y., Kiang J.E. User’s guide to the weighted-multiple-linear-regression program (WREG version 1.0): US Geological Survey Techniques and Methods, book 4, chap, viewed nd, from http://pubs. usgs. gov/tm/tm4a8, 2009, pp. 21.
39. Guseva A.I., Romanov R.M. Programma dlya EVM «Programmnoe prilozhenie dlya vizualizatsii i postroeniya nechetkikh kognitivnykh kart v zadachakh upravleniya slabo formalizovannymi sistemami», svidetel'stvo o gosudarstvennoy registratsii programmy dlya EVM № 2025660016 ot 21.04.2025. Pa-tentoobladatel' NIYaU MIFI (Rossiya) [Computer program “Software application for visualization and construction of fuzzy cognitive maps in control problems of weakly formalized systems”, certificate of state registration of computer program No. 2025660016 dated April 21, 2025. Patent holder: National Research Nuclear University MEPhI (Russia)], 2025.
40. Romanov R.M., Guseva A.I. Programma dlya EVM «Programmnoe sredstvo analiza i postroeniya re-gressionnoy modeley na osnove metoda analiticheskikh setey dlya slabo formalizovannykh sistem», svi-detel'stvo o gosudarstvennoy registratsii programmy dlya EVM № 2025686199 ot 30.09.2025. Paten-toobladatel' NIYAU MIFI (Rossiya) [Computer program “Software for analysis and construction of re-gression models based on the analytical network method for weakly formalized systems”, certificate of state registration of computer program No. 2025686199 dated September 30, 2025. Patent holder: National Research Nuclear University MEPhI (Russia)], 2025.
