Using convolutional neural networks to model the relationship between institutional investors' horizons and bank risk-taking

Document Type : Original Article

Authors

1 Department of Finance, Yazd Branch, Islamic Azad University, Yazd, Iran

2 Professor, Faculty of Economics, Management and Accounting, Department of Accounting and Finance, University of Yazd, Yazd, Iran.

3 Department of Finance, Yazd Branch, Islamic Azad University, Yazd, Iran.

Abstract

Introduction: Bank risk-taking is a fundamental component of financial system stability and is shaped by a variety of factors, including ownership structure, shareholder composition, and investor behavior. Among these, the investment horizon of institutional investors—whether short-term or long-term—plays a critical role in determining how banks respond to different types of market risk. Institutional investors with varying horizons adopt distinct approaches to oversight, resource allocation, and responsiveness to market fluctuations, which in turn can have direct implications for banks’ risk exposure. Due to the multidimensional and nonlinear nature of the relationship between investment horizon and risk-taking, traditional financial modeling techniques such as linear regression or feedforward neural networks face significant limitations. These models often fail to capture hidden patterns, nonlinear dependencies, and localized features within financial data. Therefore, the primary objective of this study is to utilize Convolutional Neural Networks (CNNs) to more accurately model the relationship between institutional investment horizon and bank risk-taking, using structured financial data from banks listed on the Tehran Stock Exchange.

Method: This research is applied in nature and follows a descriptive-correlational methodology. The statistical population consists of all active banks listed on the Tehran Stock Exchange between 2014 and 2020. Financial data related to institutional investment horizons (short-term and long-term) and key indicators of bank risk-taking were extracted and transformed into 4×4 matrices to enable convolutional processing. Three CNN architectures were designed and trained, each with a different number of filters: 64, 128, and 256. These models were developed to identify complex patterns and improve predictive accuracy in modeling the target relationship. Model performance was evaluated using standard classification metrics, including Accuracy, F1 Score, and Area Under the Receiver Operating Characteristic Curve (AUC).

Results and Discussion: The results revealed that the correlation between short-term institutional investment horizon and bank risk-taking was 0.86, significantly stronger than the correlation observed for long-term horizons, which was 0.72. This indicates that institutional investors with shorter horizons, due to their heightened responsiveness to market dynamics, play a more effective role in mitigating bank risk. Among the three CNN models, the 64-filter architecture (CNN64) demonstrated the highest predictive performance, achieving an accuracy of 0.829, an F1 score of 0.815, and an AUC of 0.842. This model successfully extracted localized features and identified complex patterns within the financial data, outperforming traditional approaches in both precision and generalizability.

Conclusion: The findings of this study confirm that Convolutional Neural Networks—particularly lightweight configurations such as CNN64—are powerful tools for analyzing complex and nonlinear relationships in financial datasets. Applying CNNs to assess the impact of institutional investment horizons on bank risk-taking not only enhances predictive accuracy but also enables deeper interpretation of market behavior and more informed investment decision-making. The emphasis on short-term horizons as a key factor in reducing bank risk offers practical implications for regulatory policy, risk governance, and strategic asset allocation in the banking sector. Future research is encouraged to explore a broader range of machine learning models, such as decision trees, ensemble methods, and deeper neural networks, and to incorporate macroeconomic variables including interest rates, inflation, and monetary policy into the analytical framework. Moreover, extending the scope of analysis to include international financial markets and longer time horizons will enhance the external validity of the findings and contribute to theoretical advancement in bank risk management.

Keywords

References

  1. Adem, K. (2022). Impact of activation functions and number of layers on detection of exudates using circular Hough transform and convolutional neural networks. Syst. Appl. 2022, 203, 117583.
  2. Aggarwal, R., Erel, I., Ferreira, M. A., & Matos, P. (2021). Does governance travel around the world? Evidence from institutional investors, Journal of Financial Economics, 139(2), 371-396.
  3. Alzubaidi, L.; Zhang, J.; Humaidi, A.J.; Al-Dujaili, A.; Duan, Y.; Al-Shamma, O.; Santamaría, J.; Fadhel, M.A.; Al-Amidie, M.; Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Big Data 2021, 8, 83.
  4. Amihud, Y., & Goyenko, R. Y. (2021). Institutional investors and liquidity. Journal of Financial Economics, 141(1), 1-20.
  5. Bae, K. H., Goyal, V. K., & Tran, A. L. (2020). Institutional herding and its price impact: Evidence from the corporate bond market. Journal of Financial Economics, 135(3), 571-594.
  6. Benabi Ghadim, Rahim, Rahmani Fard, Somayeh. (2021). The Impact of Agency Problems on the Relationship Between Institutional Investor's Short-Term Horizon and Stock Price Crash Risk. Financial Management Outlook, 11(34), 117-144. (In Persian)
  7. Bhatt, D.; Patel, C.; Talsania, H.; Patel, J.; Vaghela, R.; Pandya, S.; Modi, K.; Ghayvat, H. (2021). CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics 2021, 10, 2470.
  8. Binti Ahmad, H., Binti Azhari, A. (2022). Effects of Institutional Investors' Activism on Corporate Risk-Taking Activities, https://www.researchgate .net/ publication / 3587 41684.
  9. Chen, K.; Fu, K.; Yan, M.; Gao, X.; Sun, X.; Wei, X. (2018). Semantic segmentation of aerial images with shuffling convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 2018, 15, 173–177.
  10. Dai X., Zhang D., Lau C.K.M., Wang Q. (2023). Multiobjective portfolio optimization: Forecasting and evaluation under investment horizon
  11. Dhillon, A.; Verma, G.K. (2019). Convolutional neural network: A review of models, methodologies, and applications to object detection. Artif. Intell. 2019, 9, 85–112.
  12. Enayatpour Shiadeh, E., Gholipour Pasha, M., Derakhshan, J., Farghani, A. (2020). The Impact of Institutional Ownership on the Value and Risk of Companies Listed on the Tehran Stock Exchange. Accounting and Management Outlook, 3(23), 16-28. (In Persian)
  13. Fahlenbrach, R., & Stulz, R. M. (2021). Bank lending relationships and the use of performance-sensitive debt. Journal of Financial Economics, 140(2), 570-596.
  14. Gennaioli, N., La Porta, R., Lopez-de-Silanes, F., & Shleifer, A. (2021). Trust in banks. Journal of Financial Economics, 141(3), 17-1.
  15. Gloßner S. (2019) Investor horizons, long-term blockholders, and corporate social responsibility, Journal of Banking & Finance, 103, 78-97.
  16. Gompers, Paul A. and Ishii, Joy L. Metrick, A. (2003). Corporate Governance and Equity Prices. Quarterly Journal of Economics, 118(1), 107-155, http://dx.doi.org/10.2139/ssrn.278920
  17. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  18. Goyal, V. K., & Zhang, S. (2021). The dark side of institutional investors: Do they destroy jobs? Journal of Financial Economics, 140(1), 1-23.
  19. Hartzmark, S. M., & Sussman, A. B. (2020). Do investors value sustainability? A natural experiment examining ranking and fund flows. Journal of Financial Economics, 138(3), 803-824.
  20. Hutchinson, M., Seamer, M., Chapple, L. (2021). Institutional Investors, Risk/Performance and Corporate Governance, The International Journal of Accounting, 50(1), 302-319.
  21. Jia, R., & Zhang, H. (2021). Institutional investors and corporate social responsibility. Journal of Financial Economics, 141(1), 248-273.
  22. Khan, A.; Sohail, A.; Zahoora, U.; Qureshi, A.S. (2020). A survey of the recent architectures of deep convolutional neural networks. Intell. Rev. 2020, 53, 5455–5516.
  23. Kim D., Kim H.D., Joe D.Y., Oh J.Y.J. (2021). Institutional investor heterogeneity and market price dynamics: Evidence from investment horizon and portfolio concentration, Journal of Financial Markets, 54, 653-669.
  24. Krizhevsky, A.; Sutskever, I.; Hinton, G.E. (2017). ImageNet classification with deep convolutional neural networks. ACM 2017, 60, 84–90.
  25. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
  26. Lel U., Tepe M. (2021). Investor horizon and managerial short-termism, The Quarterly Review of Economics and Finance, 80, 1-20.
  27. Li, X., Zhang, Y., & Chen, H. (2024). Deep Learning-Based Risk Assessment in Banking: A CNN Approach to Investor Behavior Modeling. Expert Systems with Applications, 239, 120456. https://doi.org/10.48550/arXiv.2502.06847
  28. Li, Z.; Liu, F.; Yang, W.; Peng, S.; Zhou, J. (2021). A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. IEEE Trans. Neural Networks Learn. Syst. 2021, 1–21.
  29. Navarbafi M., Fallah Nejad F., Ghajar Beigi M. (2021). The Relationship Between Stock Price Crash Risk and Institutional Investment with Stock Return Emphasizing the Moderating Role of Liquidity Ratio in Companies Listed on the Tehran Stock Exchange. Scientific Quarterly Journal of Novel Research Approaches in Management and Accounting, 5(17), 155-173. (In Persian)
  30. Ni X., Peng Q., Yin S., Zhang T. (2020). Attention! Distracted institutional investors and stock price crash, Journal of Corporate Finance, 64, 366-378.
  31. Nishiwaki T. (2022). Impact of different investment horizons in heterogeneous agent models: Do long-term traders bring market stability? Journal of Economic Behavior & Organization, 196(1):393-401.
  32. Pástor, Ľ., & Veronesi, P. (2020). Inequality aversion, populism, and the backlash against globalization. Journal of International Economics, 126, 103330.
  33. Pathan S., Haq M., Faff R., Seymour T. (2021). Institutional investor horizon and bank risk-taking, Journal of Corporate Finance, 66, 102-119.
  34. Pillai, R. P., & Pushpa Latha, D. P. (2025). A Deep Learning Based Hybrid Model Using LSTM and CNN Techniques for Automated Internal Fraud Detection in Banking Systems. Journal of Information Systems Engineering and Management, 10(40s). https://doi.org/10.52783/jisem.v10i40s.7468
  35. Podukhovich D. (2023). Determinants of CEO Investment Horizon. A Literature Review, Journal of Corporate Finance Research, 17(2):95-109.
  36. Rusk, N. Deep learning. Nat. Methods 2017, 13, 35.
  37. Sadeghi Gorji, N., Mahfouzi, G., Meshki Miyaghi, M. (2016). The Impact of Different Institutional Investors on Stock Price Crash Risk in Companies Listed on the Tehran Stock Exchange, International Conference on Management and Accounting, Tehran. (In Persian)
  38. Sarraf, F, Karimi, M., Besharatpour, F. (2022). The Impact of Institutional Ownership Horizon on Corporate Social Responsibility and Stock Value of Companies Listed on the Tehran Stock Exchange. Financial Economics (Financial Economics and Development), 16(58), 173-192. (In Persian)
  39. Shen, J.; Shafiq, M.O. (2018). Deep Learning Convolutional Neural Networks with Dropout—A Parallel Approach. In Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, FL, USA; 572–577.
  40. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  41. Swapna, M.; Sharma, D.Y.K.; Prasad, D.B. (2020). CNN Architectures: Alex Net, Le Net, VGG, Google Net, Res Net. Int. J. Recent Technol. Eng. 2020, 8, 953–959.
  42. Taye, M.M. (2023). Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers 2023, 12, 91. https://doi.org/10.3390/computers12050091
  43. Wan J., Shi M., Liang Y., Qin L. (2023). Prediction method of large-diameter ball valve internai leakage rate based on CNN-GA-DBN, IEEE Sensors Journal, (99):1-1.
  44. Wang X., Wei S. (2020). Does the investment horizon of institutional investors matter for stock liquidity? International Review of Financial Analysis, 74, 366-380.
  45. Zhang, Q.; Zhang, M.; Chen, T.; Sun, Z.; Ma, Y.; Yu, B. (2019), Recent advances in convolutional neural network acceleration. Neurocomputing 2019, 323, 37–51.

 

Files

Share

How to cite

Statistics