student
student
employee
Recently, neural networks have been actively used in economic research, opening up new potential for data analysis, forecasting, and decision-making. Their capacity to identify complex nonlinear relationships, process vast amounts of information, and adapt to changing conditions makes them an invaluable tool for economists. This article explores key applications of neural networks in economics, analyzes their advantages and limitations, and discusses future development prospects of this approach. Particular attention is given to Russian research in this field and practical implementations of neural network models in financial sector, macroeconomic forecasting, and business process management.
neural networks, machine learning, economic forecasting, financial markets, data analysis, artificial intelligence in economics
1. Endal'cev D.A. Primenenie metodov glubokogo obucheniya dlya prognozirovaniya finansovyh vremennyh ryadov // Ekonomika i matematicheskie metody. 2020. T. 56. № 3. S. 45-58.
2. Lozhnikov A.V. Neyrosetevye modeli v algoritmicheskoy torgovle: teoriya i praktika. M.: Finansy i statistika, 2021. 320 s.
3. Haitov S.R., Petrova M.A. Gibridnye modeli prognozirovaniya inflyacii s ispol'zovaniem mashinnogo obucheniya // Voprosy ekonomiki. 2022. № 5. S. 78-94.
4. Smirnov A.A., Ivanova E.K. Iskusstvennyy intellekt v kreditnom skoringe: sovremennye podhody i rossiyskaya praktika // Den'gi i kredit. 2021. № 8. S. 34-49.
5. Federal'naya sluzhba gosudarstvennoy statistiki. Cifrovaya ekonomika Rossii: 2023. Statisticheskiy sbornik. M., 2023.
6. Sopina N.V., Makkaeva R.S.-A. Perspektivy vnedreniya neyrosetey i iskusstvennogo intellekta na promyshlennom proizvodstve//Journal of Monetary Economics and Management.- 2023.- №3. - S. 222-227
