Comparison of the Effectiveness of Machine Learning Models and Statistical Models in Predicting Financial Risk

Document Type : Research Paper

Authors

1 Department of Accounting, Faculty of Economics and Management, Urmia University, Urmia, Iran

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

Abstract

The purpose of this study was to compare the efficiency of machine learning models (32 models) and statistical models (14 models) in predicting the financial risk of listed 145 companies in Tehran Stock Exchange during the period 2010 to 2020 and selecting the best model using advanced optimization techniques. Findings of the research using the test of comparing the accuracy of prediction coefficients, indicates that with 99 percent confidence, the prediction accuracy of machine learning models is higher than statistical models. Also, the best machine learning model after optimization was the evolutionary support vector machine model with 99.86 percent prediction accuracy and the value of the area under the curve was 0.998. In addition, accrual financial ratios with 99.45 percent predictive accuracy and operating financial ratios with 98.62 percent predictive accuracy were able to perform better than other financial ratios in using the evolutionary support vector to predict financial risk. on the other side, the projected financial risk varied according to different industries. Therefore, it was found that machine learning models can be used as an important tool in predicting corporate financial risk due to the lack of limitations that statistical models face.

Keywords

Main Subjects

References

Aflatooni, A. (2013). Statistical analysis with EViews in accounting and financial management research: Termeh Publications. (In Persian)
Ashtab, A., Ahmadi, A. (2020). »Relationship between Readability of Financial Reports and Stock liquidity«. Journal of Financial Accounting Knowledge, 7(3), 167-194. (In Persian)
Ashtab, A., Haghighat, H., Kordestani, Gh. R. (2017). » Developing of financial distress prediction models and its effect on earnings management tools. « Doctoral dissertation, Imam Khomeini International University. (In Persian)
Boiko, M. O. (2019). »Problematic Aspects of financial risk assessment methodology in stevedoring companies«. World Science, 1(12 (52)), 32-38.
Dey, R. K., Hossain, S. Z., Rezaee, Z. (2018). »Financial risk disclosure and financial attributes among publicly traded manufacturing companies: Evidence from Bangladesh«. Journal of Risk and Financial Management, 11(3), 50.‏
Do, T., Nguyen, T., Phan, T., Dang, T. (2020). »Identifying factors influencing on financial risk of construction firms: Evidence from Vietnam stock market«. Management Science Letters, 10(11), 2411-2418.‏
Eizadinia, N., Alinaghian, N. (2010). »Investigating the Relationship between Profit Error Prediction and Financial and Business Risk in Companies Listed in Tehran Stock Exchange«. Accounting and Auditing Research, 2(7), 72-85. (In Persian)
Gotoh, J. Y., Takeda, A., Yamamoto, R. (2014). »Interaction between financial risk measures and machine learning methods«. Computational Management Science, 11(4), 365-402.
Hashemi, S., Hosseini, S., Barandan, S. (2012). »The Comparison of Incremental Information Content of Cash and Accrual Ratios for Financial performance Evaluation of Companies Using Data mining«. Journal of Financial Accounting Research, 4(2), 63-82. (In Persian)
Jin, M., Wang, Y., Zeng, Y. (2018). »Application of data mining technology in financial risk analysis«. Wireless Personal Communications, 102(4), 3699-3713.‏
Jorge, M. J., Augusto, M. G. (2016). »Is hedging successful at reducing financial risk exposure? «. Applied Economics, 48(39), 3695-3713.‏
Kang, Q. (2019). »Financial risk assessment model based on big data«. International Journal of Modeling, Simulation, and Scientific Computing, 10(04), 1950021.‏
Kardan, B., Salehi, M., Kalateh, H. (2016). »Relationship between auditor comments, discretionary accruals and financial risk«. The Financial Accounting and Auditing Researches, 8 (31), 111-125. (In Persian)
Khodaparast Salekmoalemy, A., Rezaei, F., Kheradyar, S., Vatanparast, M. (2020). »The Empirical Test of Comparing the Cost of Equity Capital Efficiency under Information Ambiguity and Value Relevance of Earning«. Accounting and Auditing Review, 26(4), 499-516. (In Persian)
Lahmiri, S. (2016). »Features selection, data mining and finacial risk classification: a comparative study«. Intelligent Systems in Accounting, Finance and Management, 23(4), pp. 265-275.‏
Mosalla, M., Moghadam, F. (2020). »Investigating the effect of financial leverage on risk and stock returns of companies listed on the Tehran Stock Exchange«. Journal of New Research Approaches in Management and Accounting, 4 (29), 32-42. (In Persian)
Nazari, A., Haji, G. A., Nobakht, J. (2019). »Investigating the Impact of Financial Crisis on Banks' Financial Risk in Iran during 2001-2017«. Journal of Applied Economics, 8 (27), 27-34. (In Persian)
Oláh, J., Kovács, S., Virglerova, Z., Lakner, Z., Kovacova, M., Popp, J. (2019). »Analysis and comparison of economic and financial risk sources in SMEs of the visegrad group and Serbia«. Sustainability, 11(7), 1853.‏
Ostadi, B., Tadrisi Pajou, P. (2019). »Presenting a model for measurement of the relationship between financial risks and financial ratios«. Empirical Studies in Financial Accounting, 16(63), 109-127. (In Persian)
Saniei Abadeh, M., Mahmoodi, S., Taherparvar, M. (2014). Applied Data Mining, Tehran, Niaz Danesh Publications, Second Edition. (In Persian).
Sun, J. (2012). »Integration of random sample selection, support vector machines and ensembles for financial risk forecasting with an empirical analysis on the necessity of feature selection«. Intelligent Systems in Accounting, Finance and Management, 19(4), 229-246.‏
Sun, J., Li, H., Adeli, H. (2013). »Concept Drift-Oriented Adaptive and Dynamic Support Vector Machine Ensemble With Time Window in Corporate Financial Risk Prediction«. IEEE Transactions on Systems, Man, and Cybernetics, Systems, 43(4), 801-813.
Svabova, L., Kral, P. (2016). »Selection of predictors in bankruptcy prediction models for Slovak companies«. Proceedings of the 10th international days of statistics and economics. Praha: Melandrium.
Valaskova, K., Kliestik, T., Svabova, L., Adamko, P. (2018). »Financial risk measurement and prediction modelling for sustainable development of business entities using regression analysis«. Sustainability, 10(7), 2144.‏
Zamani Zadeh, A., Sheri Anaghiz, S., Marfoe, M. (2019). »The effect of comparability of financial statements on the efficiency and financial risk of companies«. Master Thesis in Accounting, Allameh Tabatabai University. (In Persian)
Zhang, Y., Ji, K., An, Y. (2020). »Identification of Enterprise Financial Risk Transfer Path Based on Data Mining«. International Conference on Artificial Intelligence and Big Data (ICAIBD), Chengdu, China, pp. 101-105.

Files

History

  • Receive Date: 23 February 2021
  • Revise Date: 24 July 2021
  • Accept Date: 08 January 2023

Share

How to cite

Statistics