Methods of using artificial intelligence to forecast inflation and increase monetary policy flexibility

Cover Page

Cite item

Full Text

Abstract

the stability of the financial system depends heavily on the ability to accurately forecast inflationary trends, which becomes particularly relevant in times of global uncertainty and economic fluctuations. Innovative techniques based on artificial intelligence (AI) are making revolutionary innovations, improving the efficiency of analyzing and forecasting economic phenomena by orders of magnitude, and thus outperforming conventional econometric methods. In order to ensure timely and adaptive monetary policy, central banks are increasingly resorting to AI tools. This makes it possible to promptly adjust economic strategies in response to macroeconomic changes, thus minimizing possible risks associated with market volatility. The aim of the research was to study the methods of artificial intelligence to improve the accuracy of inflation forecasting and increase the flexibility of monetary policy, as well as to analyze their application in the macroeconomic context. The research objectives were to analyze existing AI methods and their potential in inflation forecasting; to assess the accuracy of forecasts compared to traditional econometric models; to develop a classification of AI methods according to their applicability for short-term and long-term forecasts; to identify the advantages and limitations of each method in the context of monetary policy flexibility. The author of the paper reviewed the scientific literature, studied various AI models like neural networks, random forest algorithm, textual analysis methods and advanced hybrid systems, and compared them with classical econometric models. The integration of AI opens up a wide range of prospects for monetary policy. It provides an opportunity to modify economic instruments in accordance with current trends, improving predictive capabilities. The study revealed that hybrid AI models combining the analysis of macroeconomic trends and behavioral factors, as well as the use of big data, can make a significant contribution to the interpretation of inflation dynamics.

About the authors

V. N Samonin

Russian New University

ORCID iD: 0009-0008-1949-1539

References

  1. Medeiros M., Vasconcelos G., Veiga A., Zilberman E. ?Forecasting Inflation in a DataRich Environment: The Benefits of Machine Learning Methods // Journal of Business and Economic Statistics. 2019. № 39 (1). P. 98 – 119. https://doi.org/10.1080/07350015.2019.1637745
  2. Paranhos L. ?Predicting Inflation with Neural Networks // arXiv Preprint. 2021. arXiv:2104.03757. https://doi.org/10.48550/arXiv.2104.03757
  3. Almosova A., Andresen N. ?Nonlinear Inflation Forecasting with Recurrent Neural Networks // Journal of Forecasting. 2023. № 42 (1). P. 240 – 259. https://doi.org/10.1002/for.2901
  4. Araujo G.S., Gaglianone W.P. ?Machine Learning Methods for Inflation Forecasting in Brazil: New Contenders Versus Classical Models // Latin American Journal of Central Banking. 2023. № 4 (2). P. 100087. https://doi.org/10.1016/j.latcb.2023.100087
  5. Шуляк Е. Макроэкономическое прогнозирование с использованием данных из социальных сетей // Деньги и кредит. 2020. № 81 (4). С. 86 – 112. URL: https://rjmf.econs.online/upload/iblock/d66/Makroekonomicheskoye-prognozirovaniye-s-ispolzzovaniyem-dannykh-sotsialqnykh-setey.pdf
  6. Семитуркин О., Шевелев А. Корректное сравнение прогностических характеристик моделей машинного обучения: Пример прогнозирования темпов инфляции в Сибири // Деньги и кредит. 2023. № 82 (1). С. 87 – 103. URL: https://rjmf.econs.online/upload/iblock/16d/Korrektnoye-sravneniye-prediktivnykh-svoystv-modeley-mashinnogo-obucheniya-na-primere-prognozirovaniya-inflyatsii-v-Sibiri.pdf
  7. Bo H., Niu X., Wang J. Wind Speed Forecasting System Based on the Variational Mode Decomposition Strategy and Immune Selection Multi-Objective Dragonfly Optimization Algorithm // IEEE Access. 2019. № 7. P. 178063 – 178081. https://doi.org/10.1109/ACCESS.2019.2957062
  8. Chen Z. Advancing macroeconomic models through artificial intelligence integration // Applied and Computational Engineering. 2024. № 77. Pp. 43 – 48. https://doi.org/10.54254/2755-2721/77/20240649
  9. Udo W., Toromade A.S., Chieezie N.R. AI-powered economic forecasting: challenges and opportunities in a data-driven world // Computer Science & IT Research Journal. 2022. № 3 (3). P. 74 – 91. https://doi.org/10.51594/csitrj.v3i3.1452
  10. ASM A.A., Judijanto L., Tooy D., Putra P., Hermansyah M., Kumalasanti M., Agit A. Integration of Artificial Intelligence and Macro-Economic Analysis: A Novel Approach with Distributed Information Systems // EAI Endorsed Scal Inf Syst [Internet]. 2023. № 11 (2). https://doi.org/10.4108/eetsis.4452
  11. Damasevicius R. Progress, Evolving Paradigms and Recent Trends in Economic Analysis // Financial Economics Letters. 2023. № 2 (2). P. 14. https://doi.org/10.58567/fel02020004
  12. Kumeno F. Software Engineering Challenges for Machine Learning Applications: A Literature Review // Intelligent Decision Technologies. 2019. № 13 (4). P. 463 – 476. https://doi.org/10.3233/IDT-190160
  13. Ishengoma F.R., Shao D., Alexopoulos C., Saxena S., Nikiforova A. Integration of artificial intelligence of things (AIoT) in the public sector: drivers, barriers and future research agenda // Digital Policy, Regulation and Governance. 2022. № 24 (5). P. 449 – 462. https://doi.org/10.1108/DPRG-06-2022-0067
  14. Jung J., Patnam M., Ter-Martirosyan A. An Algorithmic Crystal Ball: Forecast-based on Machine Learning // IMF Working Paper. 2018. № 18/230. 34 p. URL: https://www.imf.org/en/Publications/WP/Issues/2018/11/01/An-Algorithmic-Crystal-Ball-Forecasts-based-on-Machine-Learning-46288
  15. Байбуза И. Прогнозирование инфляции с помощью методов машинного обучения // Деньги и кредит. 2018. № 77 (4). С. 42 – 59. https://doi.org/10.31477/rjmf.201804.42
  16. Яковлева К. Оценка экономической активности на основе текстового анализа // Деньги и кредит. 2018. № 77 (4). С. 26 – 41. https://doi.org/10.31477/rjmf.201804.26
  17. Павлов Е. Прогнозирование инфляции в России с помощью нейронных сетей // Деньги и кредит. 2020. № 79 (1). С. 57 – 73. https://doi.org/10.31477/rjmf.202001.57
  18. Barkan O., Benchimol J., Caspi I., Hammer A., Koenigstein N. Forecasting CPI Inflation Components with Hierarchical Recurrent Neural Networks // International Journal of Forecasting. 2023. № 39 (3). P. 1145 – 1162. https://doi.org/10.1016/j.ijforecast.2022.04.009
  19. Ozgur O., Akko? U. Inflation Forecasting in an Emerging Economy: Selecting Variables with Machine Learning Algorithms // International Journal of Emerging Markets. 2021. https://doi.org/10.1108/IJOEM-05-2020-0577
  20. Mamedli M., Shibitov D. Forecasting Russian CPI with Data Vintages and Machine Learning Techniques // The Bank of Russia Working Paper Series. 2021. № 70. URL: https://cbr.ru/eng/ec_research/forecasting-russian-cpi-with-data-vintages-and-machine-learning-techniques/
  21. Астраханцева И.А., Герасимов А.С., Астраханцев Р.Г. Прогнозирование региональной инфляции с помощью алгоритмов машинного обучения // Известия ВУЗов ЭФиУП. 2022. № 4 (54). С. 6 – 13. https://doi.org/10.6060/ivecofin.2022544.620
  22. Джункеев У. Прогнозирование инфляции в России на основе градиентного бустинга и нейронных сетей // Деньги и Кредит. 2024. № 83 (1). С. 53 – 76. URL: https://rusbonds.ru/rb-docs/analytics/Prognozirovaniye-inflyatsii-v-Rossii-na-osnove-gradiyentnogo-bustinga-i-neyronnykh-setey.pdf

Supplementary files

Supplementary Files
Action
1. JATS XML
Download


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).