graduate student
employee
UDC 519.76
Adaptive forecasting methods enable short-term forecasting of indicator dynamics, which is often crucial in dynamic and highly volatile economic environments. A comparative analysis of various adaptive approaches to demand forecasting is conducted, highlighting their limitations and advantages. A proprietary hybrid architecture for demand forecasting in an unstable market environment is proposed, based on the concept of a state space with hierarchical correction. The proposed architecture combines macroeconomic data and microeconomic indicators in a single state space, enabling the joint processing of disparate signals: macroeconomic shocks and operational microindicators, which in standard models typically require a choice. The statistical foundation is formed by a vector error correction model that captures stable long-term dependencies; nonlinear patterns are processed by LSTM networks and gradient boosting.
adaptive methods, demand, market, instability, data, neural network, accuracy
1. Bey S.I., Kozar I.D. Modelirovanie processov krizisnogo menedzhmenta v malom i srednem biznese s ispol'zovaniem big data analitiki i scenariev prognozirovaniya ekonomicheskih spadov // Ekonomika: vchera, segodnya, zavtra. 2025. T. 15. № 6-1. S. 923-934.
2. Zmeev V.P. Sovremennoe sostoyanie problemy proektirovaniya neyrosetevoy sistemy prognozirovaniya sprosa na elektroniku s uchetom faktorov rynka i predpochteniy potrebiteley // Slavyanskiy forum. 2025. № 2 (48). S. 221-226.
3. Sennikova A.E., Starceva A.A., Fedorov N.B., Shaman A.S. Ekonometricheskoe modelirovanie sprosa na zhil'e v usloviyah izmeneniya procentnyh stavok // Vestnik Akademii znaniy. 2025. № 2 (67). S. 537-540.
4. Stepanischev S.A., Turischev D.K., Petrich A.S. Razrabotka metoda vyyavleniya strukturnyh izmeneniy v ryadah sprosa na osnove analiza dinamiki ostatkov // Molodoy uchenyy. 2025. № 17 (568). S. 360-362.
5. Yarovoy A.A. Sravnitel'nyy analiz neyrosetevyh i regressionnyh modeley prognozirovaniya potrebitel'skogo sprosa na osnove real'nyh dannyh // Myagkie izmereniya i vychisleniya. 2025. T. 92. № 7. S. 51-59.
6. Corey Ducharme, Bruno Agard, Martin Trépanier Improving demand forecasting for customers with missing downstream data in intermittent demand supply chains with supervised multivariate clustering // Journal of Forecasting. 2024. Volume 43, Issue 5. R. 82-88.
7. Qiong Wang, Linru Jiang, Qinghe Sun An Adaptive Forecasting Framework for EV Charging Demand Using Variational Mode Decomposition and Louvain Community Detection // IET Smart Grid. 2026. Volume 9, Issue 1. R. 12-18.
8. Rashmi Bareth, Anamika Yadav Daily average load demand forecasting using LSTM model based on historical load trends // IET Generation, Transmission & Distribution. 2024. Volume 18, Issue 5. R. 100-104.
9. Xun Dou, Yu He, Hanyu Yang An Adaptive Forecasting Method for Net Load Ramping Demand Based on Time–Frequency Dual-Modal Collaboration // IET Generation, Transmission & Distribution. 2025. Volume 19, Issue 1. R. 60-64.
10. Yi-Chung Hu, Li-Chin Shih A Hybrid Approach Integrating Decomposition Ensemble Forecasting With Optimal Combination Selection for Air Passenger Demand Forecasting // Journal of Mathematics. 2025. Volume 2025, Issue 1. R. 39-42.
