Intellectual capital, efficiency of financial stability and financial capital of banks with the approach of neural spatial algorithms: (Study case: Iranian and Iraqi banks)

Document Type : Research Paper

Authors

1 PhD student, Urmia University, Department of Accounting, Urmia, Iran

2 Associate Professor, Urmia University, Faculty of Economics and Management, Department of Accounting, Urmia, Iran

Abstract

The present study was conducted with the aim of investigating the effects of financial stability efficiency and intellectual capital on the financial stability of banks admitted to the stock exchanges of Iran and Iraq. This research has made use of extensive financial data of 22 Iranian banks and 44 Iraqi banks in the period from 2000 to 2023 and using machine learning approaches, spatial algorithms and neural networks for deep and multidimensional analysis of complex relationships between financial variables of these banks. The results of this research show that machine learning models, especially Bayesian deep learning and transfer neural network, have outstanding performance in predicting and analyzing the financial stability of banks. These models are able to identify hidden patterns and nonlinear relationships in financial data that traditional methods are unable to discover. The spatial vector autoregression model, with a combination of deep learning, reveals that financial stability, efficiency and intellectual capital are respectively the most important factors affecting the financial stability of banks in Iran and Iraq. These findings highlight the importance of considering spatial and intersectoral dependencies in financial analyses. In addition, the hybrid spatial panel model shows the critical role of capital adequacy in financial stability and simultaneously reveals the negative effects of banking concentration, state ownership and high financial leverage on financial stability. These results highlight the need to review policies related to ownership structure and risk management in the banking system.

Keywords

Main Subjects

Files

History

  • Receive Date: 21 September 2024
  • Revise Date: 16 November 2024
  • Accept Date: 22 December 2024

Share

How to cite

Statistics