Title :
Study on Commercial Bank Branches Performance Evaluation Using Self-Adaptive RBFNN and UDM
Author :
XiaoHua, Diao ; Shiying, Kang
Author_Institution :
RongZhi Coll., Chongqing Technol. & Bus. Univ., Chongqing, China
Abstract :
The commercial bank branches performance evaluation indicator system and it´s detail normalization piecewise function are established in the paper. By using scientific Uniform Design method(UDM), the large number of representative uniformly distributed samples are designed for training RBFNN and solving the problem of RBFNN model´s poor generalization ability. The experiments show the result of self-adaptive RBFNN evaluation is very close to the expected result of the experts fuzzy comprehensive evaluation(FCE). The evaluation method realizes the self-adaptive and non-linear approaching ability, meantime conquers the capability limitation of traditional BP network and non-preciseness of lacking experiment design, and avoids the subjectivity and uncertainty of traditional evaluation.
Keywords :
backpropagation; bank data processing; fuzzy set theory; radial basis function networks; BP network; commercial bank branch performance evaluation indicator system; fuzzy comprehensive evaluation; normalization piecewise function; radial basis function neural network; self-adaptive RBFNN; uniform design method; Commercial bank branches performance evaluatio; Radial Basis Function neural network (RBFNN); The generalization ability; nearest neighbor-clustering algorithm(NNCA);
Conference_Titel :
Computational Intelligence and Security (CIS), 2010 International Conference on
Conference_Location :
Nanning
Print_ISBN :
978-1-4244-9114-8
Electronic_ISBN :
978-0-7695-4297-3
DOI :
10.1109/CIS.2010.129
