In the context of the digital transformation of public administration and the need to improve the efficiency of budget planning, the development and implementation of intelligent methods for forecasting budget financing volumes has become a pressing issue. Based on the analysis, the authors highlight the specific features of forecasting cash execution of expenditures under government programs in Russia at the regional level, which currently reduce the quality and effectiveness of forecasting. The article examines some theoretical and applied aspects of using time series models and machine learning algorithms to forecast expenditures under government programs. International experience with various models is examined, and the advantages and limitations of various approaches for Russian practice are identified. An approach to building a forecasting system architecture based on the Electronic Budget State Information System (GIIS) and modern models is proposed.
government programs, regional budget expenditure forecasting, time series, machine learning, budget financing forecasting models
1. Federal'nyy zakon ot 7 maya 2013 goda №104-FZ «O vnesenii izmeneniy v Byudzhetnyy kodeks Rossiyskoy Federacii i otdel'nye zakonodatel'nye akty Rossiyskoy Federacii v svyazi s sovershenstvovaniem byudzhetnogo processa»/ Informacionno-pravovaya sistema «GARANT». URL:https://base.garant.ru/70373192/
2. Analiz deystvuyuschey praktiki formirovaniya byudzhetnyh prognozov sub'ektov Rossiyskoy Federacii. / Oficial'nyy sayt Minfina RF. URL: https://minfin.gov.ru/ru/document/?id_4=132277-analiz_deistvuyushchei_ praktiki_formirovaniya_byudzhetnykh_prognozov_subektov_rossiiskoi_federatsii&ysclid=mnbmobcq61846879825
3. Prikaz Minfina Rossii ot 9 iyunya 2025 g. № 69n «Ob utverzhdenii Poryadka razrabotki i utverzhdeniya glavnymi administratorami dohodov federal'nogo byudzheta s ispol'zovaniem gosudarstvennoy integrirovannoy informacionnoy sistemy upravleniya obschestvennymi finansami «Elektronnyy byudzhet» metodiki prognozirovaniya postupleniy dohodov v byudzhety byudzhetnoy sistemy RF»/ Informacionno-pravovaya sistema «GARANT». URL: https://www.garant.ru/hotlaw/minfin/1885277/
4. Metodicheskie rekomendacii dlya sub'ektov Rossiyskoy Federacii po poryadku publikacii finansovoy i inoy informacii o byudzhete i byudzhetnom processe, podlezhaschey razmescheniyu v otkrytom dostupe na edinom portale byudzhetnoy sistemy Rossiyskoy Federacii. / Oficial'nyy sayt Minfina RF. URL:https://sudact.ru/law/metodicheskie-rekomendatsii-dlia-subektov-rossiiskoi-federatsii-po_1/
5. Baranova E. S. Problemy formirovaniya byudzhetov sub'ektov Rossiyskoy Federacii v period finansovo-ekonomicheskogo krizisa / E. S. Baranova, N. V. Yakovleva // Finansovye aspekty strukturnyh preobrazovaniy ekonomiki. – 2015. – № 1. – S. 5-9.
6. Begchin N. A. O edinom poryadke vneseniya izmeneniy v svodnuyu byudzhetnuyu rospis', limity byudzhetnyh obyazatel'stv, informaciyu ob ob'ektah kapital'nyh vlozheniy, pasporta nacproektov i gosprogramm. Osobennosti formirovaniya prognoza kassovogo ispolneniya rashodov federal'nogo byudzheta./ Oficial'nyy sayt Minfina RF. URL: https://minfin.gov.ru/common/upload/library/2023/12/main/Begchin_N.A..pdf
7. Istomina N.A. O suschnosti i sovremennoy praktike primeneniya metodov byudzhetnogo planirovaniya i prognozirovaniya// Nacional'nye interesy: prioritety i bezopasnost'. 2012. №37. URL: https://cyberleninka.ru/article/n/o-suschnosti-i-sovremennoy-praktike-primeneniya-metodov-byudzhetnogo-planirovaniya-i-prognozirovaniya (data obrascheniya: 31.03.2026).
8. Kozyreva S. E. Razvitie i ispol'zovanie iskusstvennogo intellekta v sfere nalogooblozheniya/ S. E. Kozyreva, N. V. Yakovleva // Ekonomika i biznes: teoriya i praktika. – 2023. – № 6-2(100). – S. 14-16.
9. Markova A.A. Gosudarstvennye programmy kak instrument byudzhetnogo planirovaniya i prognozirovaniya// Vestnik RUDN. Seriya: Ekonomika. 2013. №5. URL: https://cyberleninka.ru/article/n/gosudarstvennye-programmy-kak-instrument-byudzhetogo-planirovaniya-i-prognozirovaniya (data obrascheniya: 30.03.2026).
10. Prosalova V.S. Vozmozhnosti primeneniya neyronnyh setey v ekonomike// Vestnik Altayskoy akademii ekonomiki i prava. 2024. № 8-2. S. 325-331; URL:https://vaael.ru/ru/article/view?id=3663 (data obrascheniya: 30.03.2026).
11. Rubanova D. V. Razvitie cifrovizacii v ekonomike Rossii / D. V. Rubanova, N. V. Yakovleva // Ekonomika i biznes: teoriya i praktika. – 2024. – № 11-3(117). – S. 72-74.
12. Zwiller-Panicz P., Novikova M., Gaudreau K., Paslawski M. Applying Random Forest Algorithms to Enhance Expenditure Predictions in Government Grants and Contributions Programs// Statistics Canada. – 2025. URL: https://www.statcan.gc.ca/en/random-forest-algorithms
13. Gür Y.E., Yıldız A., Ünal E. Advanced AI Models for Future Forecasting of Budget Expenditures via Machine Learning and Deep Learning// Panoeconomicus. – 2025.– P.1 – 36. URL:https://panoeconomicus.org/index.php/ jorunal/article/view/2307/916
14. Deep Neural Network-based Consumer Price Index Forecasting in the Case of Macau// ACM International Conference Proceedings. – 2025. URL:https://dl.acm.org/doi/10.1145/3745238.3745288
