Designing an Intelligent Model for Predicting Corporate Financial Distress Using Deep Learning Algorithms and Behavioral Indicators of the Capital Market
Keywords:
Financial distress, deep learning, capital market, behavioral indicators, bankruptcy prediction, thematic analysis, financial artificial intelligenceAbstract
This study aimed to design an intelligent model for predicting corporate financial distress by integrating financial indicators, behavioral capital market indicators, and deep learning capabilities from the perspective of finance, accounting, capital market, and data analytics experts. This study adopted a qualitative design based on thematic analysis. The participants consisted of financial experts, accounting and finance academics, capital market analysts, risk managers, and data science specialists in Tehran. Purposeful sampling and snowball sampling were used, and interviews continued until theoretical saturation was achieved. A total of 22 participants took part in the study. Data were collected through semi-structured interviews. After obtaining informed consent, all interviews were recorded, transcribed, and coded. Data analysis was conducted through open, axial, and selective coding using NVivo software. Data analysis resulted in 412 initial codes, 64 concepts, 17 subcategories, and five main categories. The main categories included “financial and accounting infrastructure of distress,” “behavioral and market microstructure indicators,” “data architecture and deep learning algorithms,” “interpretability, validation, and bias control,” and “institutional requirements and decision-making applicability.” The findings indicated that effective financial distress prediction cannot rely solely on accounting ratios. Instead, historical financial data, market data, trading behavior, news sentiment, and data governance requirements should be integrated into a dynamic, multi-source framework. The proposed model conceptualizes financial distress as a gradual, multidimensional phenomenon shaped by the interaction between firms’ financial conditions and behavioral market reactions. Therefore, early warning systems should move beyond static and single-source models toward intelligent, interpretable, time-sensitive, and institutionally embedded models. The proposed model can assist corporate managers, auditors, investment analysts, regulatory bodies, and creditors in early risk identification and improved financial decision-making.
Downloads
References
Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4), 589–609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. The Journal of Finance, 61(4), 1645–1680. https://doi.org/10.1111/j.1540-6261.2006.00885.x
Campbell, J. Y., Hilscher, J., & Szilagyi, J. (2008). In search of distress risk. The Journal of Finance, 63(6), 2899–2939. https://doi.org/10.1111/j.1540-6261.2008.01416.x
Charmaz, K. (2014). Constructing grounded theory (2nd ed.). Sage.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
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
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. Sage.
Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. The Journal of Finance, 66(1), 35–65. https://doi.org/10.1111/j.1540-6261.2010.01625.x
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, 30, 4765–4774.
Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research, 18(1), 109–131. https://doi.org/10.2307/2490395
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778
Shumway, T. (2001). Forecasting bankruptcy more accurately: A simple hazard model. The Journal of Business, 74(1), 101–124. https://doi.org/10.1086/209665
Strauss, A., & Corbin, J. (2015). Basics of qualitative research: Techniques and procedures for developing grounded theory (4th ed.). Sage.
Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139–1168. https://doi.org/10.1111/j.1540-6261.2007.01232.x
