Developing a Deep Learning-Based Model for Predicting Financial Crises Using Macroeconomic Indicators and Capital Market Data
Keywords:
Financial crisis, Deep learning, Macroeconomic indicators, Capital market, Early warning system, Thematic analysis, Risk prediction.Abstract
This study aimed to develop a conceptual model for predicting financial crises by integrating deep learning techniques, macroeconomic indicators, capital market data, and expert perspectives in finance, economics, and data science. This qualitative study employed thematic analysis. The participants consisted of 18 experts from Tehran, including finance specialists, economists, capital market analysts, bank risk managers, data science professionals, and financial policy experts. Participants were selected through purposive and snowball sampling. Data were collected using semi-structured interviews and continued until theoretical saturation was achieved; initial saturation occurred at the sixteenth interview, and two additional interviews were conducted to confirm saturation. The interview data were analyzed using NVivo software through open, axial, and selective coding. Credibility and trustworthiness were enhanced through member checking, peer review, audit trail documentation, and constant comparison of codes and themes. The analysis resulted in five main categories: integration of macroeconomic and capital market data, deep learning architecture for detecting pre-crisis patterns, model interpretability and validation, data governance and model risk management, and institutional application of early warning systems. Participants emphasized that financial crisis prediction is not merely a computational problem; rather, it requires multi-source data integration, sequence-based models such as LSTM, interpretable risk indicators, tiered warning mechanisms, and institutional capacity for timely intervention. The proposed model suggests that a financial crisis prediction system should move beyond numerical forecasting and operate as a decision-support framework for regulators, banks, financial institutions, and capital market actors. Integrating deep learning with macroeconomic indicators, trading data, and explainability layers may facilitate early identification of financial vulnerabilities, reduce policy surprise, and improve market resilience.
Downloads
References
Berg, A., & Pattillo, C. (1999). Are currency crises predictable? A test. IMF Staff Papers, 46(2), 107–138.
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Creswell, J. W., & Poth, C. N. (2018). Qualitative inquiry and research design: Choosing among five approaches (4th ed.). SAGE Publications.
Demirgüç-Kunt, A., & Detragiache, E. (1998). The determinants of banking crises in developing and developed countries. IMF Staff Papers, 45(1), 81–109.
Fethi, M. D., & Pasiouras, F. (2010). Assessing bank efficiency and performance with operational research and artificial intelligence techniques: A survey. European Journal of Operational Research, 204(2), 189–198.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
Hennink, M. M., Kaiser, B. N., & Marconi, V. C. (2017). Code saturation versus meaning saturation: How many interviews are enough? Qualitative Health Research, 27(4), 591–608. https://doi.org/10.1177/1049732316665344
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Kaminsky, G. L., Lizondo, S., & Reinhart, C. M. (1998). Leading indicators of currency crises. IMF Staff Papers, 45(1), 1–48. https://doi.org/10.2307/3867328
Laeven, L., & Valencia, F. (2018). Systemic banking crises revisited (IMF Working Paper No. 18/206). International Monetary Fund. https://doi.org/10.5089/9781484376379.001
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. SAGE Publications.
Lo Duca, M., & Peltonen, T. A. (2013). Assessing systemic risks and predicting systemic events. Journal of Banking & Finance, 37(7), 2183–2195.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems.
Nabipour, M., Nayyeri, P., Jabani, H., Shahab, S., & Mosavi, A. (2020). Predicting stock market trends using machine learning and deep learning algorithms via continuous and binary data: A comparative analysis. IEEE Access, 8, 150199–150212. https://doi.org/10.1109/ACCESS.2020.3015966
Sevim, C., Oztekin, A., Bali, O., Gumus, S., & Guresen, E. (2014). Developing an early warning system to predict currency crises. European Journal of Operational Research, 237(3), 1095–1104.
