In this study, an integrated soft computing method is proposed to solve the performance prediction of commercial banks. The proposed model not only shows how to explore the implicit patterns from historical data, but also supports to provide guidance regarding the performance categorization of banks on each attribute. A group of commercial banks in Taiwan is analyzed to construct the model, and three sample banks are tested (ranked) to validateit. The result provides understandable insights and applicable rules regarding the performance prediction of commercial banks in practice.