基于贝叶斯网络的我国商业银行声誉风险度量研究  

Measurement Research of Domestic Commercial Banks' Reputational Risk Based on Bayesian Network

作　　者：张强[1] 胡敏[1] 

机构地区：[1]湖南大学金融与统计学院,湖南长沙410079

出　　处：《财经理论与实践》2014年第2期2-8,共7页The Theory and Practice of Finance and Economics

基　　金：国家社会科学基金重点项目(12AZD035)

摘　　要：根据我国商业银行声誉风险分布情况，构建商业银行声誉风险评价体系。运用贝叶斯网络模型，考量国有商业银行2007～2012年间的485组声誉损失数据，得出声誉风险的超极限矩阵。实证表明，企业感召力缺乏、产品和服务缺陷、银行风险控制不足等成为中国商业银行声誉风险的主要因素，银行应有针对性地对其进行有效规避和分散。According to the actual situation of China＇s commercial banks reputational risk distribution,We developed a commercial bank reputational risk evaluation system in this paper. A Bayesian network model was built to analyze the loss data of 485 state-owned commercial bank group＇s reputation between 2007~2012, and then the over limit matrix of Chinese commercial banks reputational risk was derived. The empirical evidence showed that lack of charisma, and product and service defects, inadequate bank risk control are the main factors causing reputational risks of commercial banks, so the banks should take specific measures to effectively avoid and diversify risks.

关 键 词：贝叶斯网络 商业银行 声誉风险 

分 类 号：F83[经济管理—金融学]