Chinese bank efficiency during the global financial crisis: A combined approach using satisficing DEA and Support Vector Machines

The paper examines Chinese bank efficiency with a unique sample of 127 banks during the peak period of the global financial crisis. We apply an innovative Data Envelopment Analysis method under a stochastic environment. In the first stage, within the ambit of the satisficing Data Envelopment Analysis model, the probabilities of achieving a minimal performance threshold are computed in a stochastic way. In the second subsequent stage, Support Vector Machine regression is applied to discriminate between high/low efficiency groups within each performance threshold. The results reveal that the overall efficiency level of the Chinese banks remains still low. This is considerably determined by the contextual variables of the ownership structure and cost structure of the Chinese banks. Policy implications are derived how to improve the corporate governance and credit allocation.