【摘要】 在广泛选取原始指标的基础上,建立了基于主成分分析法的商业银行效率评价指标体系,建立了基于BP神经网络的商业银行效率评价模型.采用改进的主成分分析法建立了新的指标体系,用7个指标保留了92%的原始信息,并避免了指标间相关性对后期评价的影响;运用斜交旋转法,得到了对商业银行效率影响较显著的7个指标因素;采用均值法对原始数据进行标准化处理,保留了指标间的差异信息和相互影响信息;利用BP神经网络避免了传统评价方法中人为主观因素和模糊随机因素的影响.更多还原

【Abstract】 On the ground of the widely chosen efficiency indexes of commercial banks,an index system based on principal component analysis and an efficiency appraisal model based on BP neural network are established.The new index system is built based on improved principal component analysis which keeps 92% of the original information with 7 indexes and avoids the influence of the correlation between different indexes on later appraise.7 mainly influencing factors are found through direct oblimin method.The information of diversity and inner influence between different indexes are kept through average-standard-method.An appraisal model based on BP neural network is set up which gets rid of the influence of the factitious subjective factors and fuzzy stochastic ones.更多还原