Bank efficiency estimation in China: DEA-RENNA approach
研究提出新DEA模型评估39家中国商业银行2010-2018年效率，并用神经网络分析效率与银行规模、盈利等变量的关系，发现国有银行效率最高，农村商业银行最低。
Abstract The current study proposes a new DEA model to evaluate the efficiency of 39 Chinese commercial banks over the period 2010–2018. The paper also, in the second stage, investigates the inter-relationships between efficiency and some bank-specific variables (i.e. bank profitability, bank size, expenses management, traditional business and non-traditional business) under the Robust Endogenous Neural Network Analysis. The findings suggest that the sample of Chinese banks experiences a consistent increase in the level of bank efficiency up to 2015; the efficiency score is 0.915, after which the efficiency level declines and then experiences a slight volatility, while finally ending up with an efficiency score of 0.746 by the end of 2018. We also find that among different bank ownership types, the state-owned banks have the highest efficiency, the rural commercial banks are found to be least efficient and the foreign banks experience the strongest volatility over the examined period. The second-stage analysis shows that bank size exerts a positive influence on the development of non-traditional banking business and a proactive expense management, bank size and non-traditional businesses have a positive impact on efficiency levels, while bank profitability, traditional businesses and expenses management have negative influences on bank efficiency.