Bank Stock Leading Indicators and Extraction of Trigger Points

Abstract

Financial crises are typically cause by a chain of credit contractions, which in turns could be caused by the rapid worsening of indexes that indicate people’s psychology, such as bank stock prices. Therefore, the prediction of bank stocks is especially important. The purpose of this analysis is to identify trigger points where bank stocks rise or fall by extracting what common points existed in financial economic indicators immediately before significant fluctuations of bank stocks occurred in the past. To conduct discriminant analysis, we used the logistic regression analysis, Support Vector Machine, J48, and the random forest. Comparison of discriminant error rates by using each analysis method confirmed that the random forest method showed the highest precision level. We also tried to extract highly important variables. This attempt showed that the following financial economic indicators are important indicators that could have an influence on bank stock movements: Money multiplier, 10-year yield of government bonds, current bank deposits, M2/nominal GDP, and repayment years for corporation borrowing.