A Hybrid System by the Integration of Case-based Reasoning with Support Vector Machine for Prediction of Financial Crisis

The prediction of business crises is an important academic topic of which many have used artificial intelligence methods to build an early warning system for this purpose. The objective of this study is to enhance the accuracy in predicting business crises by proposing an innovative model that combines financial variables with a system that integrates Case Based Reasoning (CBR) model with a Support Vector Machine (SVM) technique. This study is divided into three major steps: First, Stepwise Regression Analysis (SRA) is applied to the input set in selection of the most important factors; second, Case Based Reasoning (CBR), a clustering method, is employed to separate the case library into smaller clusters; and lastly, a Support Vector Machine (SVM) model is established and prediction results are being generated. In comparison with other methods, the proposed CBR-SVM model outperforms other prediction models as the prediction accuracy of business crises are being enhanced while it simultaneously produces valuable information for business owners and investors.