Authors : Aysha Bibi

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/2yh8b8va

Scribd : https://tinyurl.com/y777aptx

DOI : https://doi.org/10.38124/ijisrt/25apr1302

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Artificial Intelligence (AI) is revolutionizing the field of economics and finance, offering data-driven techniques for improving the analysis of macroeconomic policies. Among these, the integration of AI-based natural language processing (NLP) tools with monetary policy analysis is an emerging frontier. Central banks around the world, particularly the European Central Bank (ECB), rely heavily on public communication to shape market expectations and manage economic stability. However, the interpretation of these communications has traditionally been subjective and inconsistent. This research explores how AI, through machine learning-powered text analysis, can significantly improve the forecasting and interpretation of central bank policy decisions. Using real-world ECB statements as a dataset, the study applies NLP models to classify policy sentiment into expansionary, restrictive, or neutral categories. Findings indicate that AI-based analysis can uncover subtle linguistic cues in policy texts, enhance predictive models when combined with macroeconomic indicators, and ultimately improve decision-making for policymakers, investors, and economists. This paper highlights the transformative role AI is playing in modern monetary policy frameworks and offers a roadmap for its future integration into central banking systems.

References :

1. Bagnoli, P., & Giannone, D. (2019). Monetary policy communication and market expectations. Journal of Economic Perspectives, 33(4), 23-42. https://doi.org/10.1257/jep.33.4.23
2. Bernanke, B. S., & Gertler, M. (2015). Monetary policy and economic stability. Brookings Papers on Economic Activity, 2015(1), 1-88. https://doi.org/10.2139/ssrn.2560591
3. Christensen, J. H. E., & Rudebusch, G. D. (2012). The response of the US economy to changes in monetary policy. European Economic Review, 56(5), 973-990. https://doi.org/10.1016/j.euroecorev.2012.03.008
4. Eichengreen, B., & Gupta, P. (2017). The euro and the European economy: The state of the union. Oxford Review of Economic Policy, 33(3), 426-451. https://doi.org/10.1093/oxrep/grx025
5. Hays, C. L., & Dube, G. (2018). AI and economic forecasting: A study of sentiment analysis applications. International Journal of Forecasting, 34(2), 182-195. https://doi.org/10.1016/j.ijforecast.2017.10.007
6. Kurov, A. (2019). Monetary policy and central bank communication. Journal of Financial and Quantitative Analysis, 54(6), 2351-2375. https://doi.org/10.1017/S0022109019000601
7. Loughran, M., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. Journal of Finance, 66(1), 35-65. https://doi.org/10.1111/j.1540-6261.2010.01625.x
8. Rüdiger, J., & Weber, S. (2018). Sentiment analysis and its economic implications: A study on central bank communications. Journal of Monetary Economics, 99(4), 100-118. https://doi.org/10.1016/j.jmoneco.2018.02.001
9. Sims, C. A. (2018). Central bank communication: Methods and outcomes. The Review of Economic Studies, 85(3), 1909-1946. https://doi.org/10.1093/restud/rdx045
10. Zohar, L., & Hall, S. (2017). Forecasting macroeconomic variables with machine learning models. Journal of Applied Econometrics, 32(6), 1051-1076. https://doi.org/10.1002/jae.2529