Optimal credit risk model based on metaheuristic particle swarm algorithm and multilayer perceptron neural network

Document Type : Research Paper

Authors

1 Department of Financial Engineering, Aliabad Katoul Branch, Islamic Azad University, Aliabad Katoul, Iran

2 Department of Management, faculty of social sciences and economics, Alzahra University, Tehran, Iran

3 Department of Accounting, Aliabad Katoul branch, Islamic Azad University, Aliabad Katoul, Iran

Abstract

The present study aims to develop a credit portfolio optimization model in the banking industry using a multilayer perceptron artificial neural network with a metaheuristic particle swarm algorithm. Risk, having its own complexity, is a basic concept in financial markets. Since there is no clear picture of risk realization, financial markets are in need of risk control and management approaches. With regard to data collection, this is a descriptive study and regarding the nature and purpose of the research, it is a developmental-applied one. The statistical population of the research includes all facility files of the last 10 years and the financial statements of a commercial bank, selected by census method. The risk criteria used in the models include fuzzy Value-at-Risk (VaR), fuzzy conditional Value-at-Risk (CVAR), fuzzy average Value-at-Risk(AVaR), fuzzy lower absolute deviation(LAD), fuzzy Semi-Kurtosis, and fuzzy Semi-Entropy. The research models were implemented using a three-layer perceptron artificial neural network. MATLAB software was used to conduct the research. The results indicate that the performance of the fuzzy average Value-at-Risk model is better than other models in evaluating optimal portfolios due to the lower mean squared error rate in generating more revenue. Therefore, it is recommended that the above model be used to optimize the credit portfolio.

Keywords

[1] M. Pendar R. and Veisi, Investigation of various risks in the usury-free banking system (a the combination of Dematel and Interpretive Structural Modeling), Finan. Econ. 14(51) (2020) 29–54.
[2] M. Delvi, E. Baghi, A. Abdolbaghi J. and Kazemi, The application of the multi-purpose genetic algorithm in optimizing bank’s facilities portfolio (A case study of the granted facilities in one of the commercial banks of Iran), Account. Audit. Res. 7(27) (2015) 100–120.
[3] H. Markowitz, Portfolio selection, J. Finance 7(1) (1952) 77–91.
[4] S.A. Hoseini, Z. Pourzamani and A. Jahanshad, Providing a Model for Selecting the Optimal Stock Portfolio Using Salp Swarm Algorithm and Multilayer Perceptron Neural Networks, Finan. Engin. Securities Manag. (Portfolio Management) 11(44) (2020) 479–503.
[5] L.V. Fausett, Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice-Hall, 1994.
[6] A. Arabmazar and P. Ruintan, Determinants of Credit Risk among Bank Clients A Case Study; Agricultural Bank of Iran, J. Iran. Econ. Essays 3(6) (2006) 46–82.
[7] G. Askarzadeh, Mathematical modeling to determine the optimal portfolio of lending facilities in financial and credit institutions, Andishe Sadegh Quart. 23 (2006) 107–130.
[8] M.B. Minhaj, Fundamentals of Neural Networks and Computational Intelligence, Amirkabir University of Technology Press, Tehran, 2018.
[9] R. Kiyani Ghalehno, S. Niroomand, H. Didekhani and A. Mahmoodirad, A multi-objective formulation for portfolio optimization of credit institutions branches: case study of Keshavarzi bank of Sistan and Baloochestan, J. Decis. Operat. Res. Inpress (2021).10.22105/dmor.2021.257591.1260.
[10] S. Naji Esfahani and M. Rastegar, Customers’ credit risk evaluation using LINMAP analysis (A case study on an Iranian Commercial Bank), Econ. Model. 12(44) (2019) 143–161.
[11] H. Mirzaei and I. Karimi Asl, The threshold modeling of internal factors for debt settlement of Gharz-ul-Hasna facilities (Gharz-ul-Hasna Resalat Bank), Finan. Econ. 12(42) (2018) 75–98.
[12] P. Artzner, F. Elbaen, J.M. Eber and D. Heath, Coherent measures of risk, Math. Finan. 9(3) (1999) 203–228.
[13] S. Guo, L. Yu, X. Li and S. Kar, Fuzzy multi-period portfolio selection with different investment horizons, European J. Operat. Res. 254(3) (2016) 1026–1035.
[14] B. Liu and D. Liu, A survey of credibility theory, Fuzzy Optim. Decision Mak. 5(4) (2002) 387–408.
[15] A. LotfiZadeh, Fuzzy sets as a basis for a theory of possibility, Fuzzy Sets Syst. 100(1) (1999) 9–34.
[16] Metawa, N. Loan portfolio optimization using genetic algorithm: A case of credit constraints, Cairo, 12th Int. Comput. Engin. Conf. (2016) 59–64.
[17] M.J. Mohaqeq Nia, M.A. Dehghan Dehnavi and M. Bai, The effect of internal and external factors of the banking industry on the credit risk of banks in Iran, Finan. Econ. 13(46) (2019) 127–144.
[18] S. T. Rachev, S. V. Stoyanov and F.J. Fabozzi, Advanced StochasticModels, Risk Assessment, and Portfolio Optimization: The Ideal Risk, Uncertainty, and Performance Measures, (Vol. 149). John Wiley & Sons, 2008.
[19] R.T. Rockafellar, S. Uryasev M. and Zabarankin, Generalized deviations in risk analysis, Finance Stochast. 10(1) (2006) 51–74.
[20] C. Roulet, Basel III: Effects of capital and liquidity regulations on European bank lending, J. Econ. Busin. 95 (2017) 26–46.
[21] W.C. Sharpe, J.W. Bailey and G.J. Alexander, Investments, Prentice Hall PTR, 1998.
[22] T. Morris and J. Comeau, Portfolio creation using artificial neural networks and classification probabilities: a Canadian study Finan. Mark. Portfolio Manag. 34 (2020) 133—163.
Volume 13, Issue 1
March 2022
Pages 1573-1586
  • Receive Date: 17 September 2021
  • Revise Date: 24 October 2021
  • Accept Date: 05 November 2021