Machine Learning Models to Predict Shareholder Returns in the Banking Industry

Abstract

Competitive pressures have steadily driven commercial banks to strategically focus on generating returns to shareholders. This research article purpose is to analyze and provide a summary about the impacts of key financial ratios (key metrics) on the effectiveness and efficiency of commercial banking industry, which reflects on the shareholder return of these banks, using machine learning and the official data of the banking industry in the USA. In this article, we study key metrics for commercial banks, and analyze annual financial and operating data of some biggest, publicly traded commercial banks in the USA in order to find out some predictive models using machine learning algorithms, particularly for panel data, and therefore, to give investors, shareholders, or asset managers a reliable tool to evaluate and forecast the performance of commercial banks.