Prediction of Banks Efficiency Using Feature Selection Method: Comparison between Selected Machine Learning Models

Abstract

This study aims to examine the main determinants of efficiency of both conventional and Islamic Saudi banks and then choose the best fit model among machine learning prediction models (i.e., support vector machine (SVM), Chi-squared automatic interaction detector (Chaid), linear regression, and neural network (NN)). The data were collected from the annual financial reports of Saudi banks from 2014 to 2018. The Saudi banking sector consists of 11 banks, 4 of which are Islamic. In this study, the major financial ratios are subgrouped into the profitability ratios, managerial practices, asset and loans, capital adequacy ratios, and liquidity. First, regression analysis is implemented with efficiency ratio as a dependent variable and the proxies of banks’ profitability, liquidity, asset quality, management ratios, and capital adequacy ratios as independent variables. Next, the feature selection is applied for different prediction models. Subsequently, 4 prediction models (i.e., SVM, CHAID, linear regression, and a neural network) were developed to choose the best fit. The performance metrics have also been evaluated. Regression results exhibit that the efficiency of both conventional and Islamic banks is highly affected by profitability, liquidity, and managerial practices. Finally, we choose the best prediction model with the highest R2 in the training and the testing phases with/out feature selection that is the CHAID model. The best predictors of cost efficiency for Saudi banks are the capital ratios, namely, CAR total and CAR tier 1. Findings are theoretically and practically important to academics, investors, and policymakers. Policymakers can benefit from the novelty of this study in building an early warning system using the CHAID model to predict different financial distress scenarios.

Dự báo hoạt động ngân hàng bằng thuật toán rừng ngẫu nhiên

“…Kết quả cho thấy cả ba kỹ thuật đều cho kết quả tương đối cao giống nhau, nhưng kỹ thuật cây quyết định J48 có hiệu quả tốt nhất với độ chính xác là 98,85%. Trong nghiên cứu của Assous (2022) đã sử dụng bốn kỹ thuật trí tuệ nhân tạo để phát triển mô hình dự báo hiệu quả hoạt động của các ngân hàng Saudi. Kỹ thuật cho độ chính xác cao nhất là kỹ thuật tự động tìm kiếm tương tác Chi-squared.…”

Saudi Green Banks and Stock Return Volatility: GLE Algorithm and Neural Network Models

“…Yet, scholars infrequently build prediction models using machine learning techniques for structuring a robust system to predict Saudi sustainable banks. Finally, these advanced prediction models become very important because of the ability to determine the best parameters that can be used for the future forecast (Assous (2022) and Al-Najjar (2022a)). In Assous (2022), the researcher examined Saudi banks' efficiency using feature selection and different machine learning models.…”

“…Finally, these advanced prediction models become very important because of the ability to determine the best parameters that can be used for the future forecast (Assous (2022) and Al-Najjar (2022a)). In Assous (2022), the researcher examined Saudi banks' efficiency using feature selection and different machine learning models. Furthermore, Al-Najjar (2022a) applied artificial neural networks to investigate the comovement between the Saudi stock market and emerging and international stock markets.…”

Developing Machine Learning Techniques to Investigate the Impact of Air Quality Indices on Tadawul Exchange Index

“…. Research Methodologye research methodology is built after developing different nonlinear prediction models based on neural networks, support vector machines (SVM), Quick Unbiased Efficient Statistical Tree (QUEST), Tree-AS, random forest, CHAID, linear regression, generalized linear regression, and CR-Tree models[33][34][35][36]. After extensive study of previous work in the field, the models are considered to extract the most important prediction models in developing stock market prediction models.…”