Research On Location And Evaluation Of Bank Business Network Based On BP Neural Network

With the development of economy, the deepening of opening up, China is gradually opening the banking financial services, and the financial institutions faces more severe market competition and increasingly complex economic environment。The bank outlets location has to face the problem that the banking financial institutions needs to solve urgently, and how to choice scientific and reasonable location is particularly important.Banking financial institutions needs to consider the factors is very complex when they choices the locations. The factors are related, influenced deeply, and it is difficult to accurately described in mathematical model, and the relationship of the results and factors is nonlinear, and the traditional location method has certain drawbacks in the forecast, it is difficult to really provide theory support for the policy makers. Neural network technology, has grew up with the time development, the BP network does not need to build mathematical equations to describing the mapping relationship,and it can learn and store a lot of input- output model of nonlinear mapping, due to its relatively simple and flexible structure,it is used widely.This article introduces the characteristics of neural network firstly,and discusses the feasibility of its application on site selection problem. Combined with factors of outlets location, this paper determines the geographical factors, the regional economic factors, traffic conditions, factors affecting population distribution, enterprise, public service facilities, industry competition factors for the influence of input factors, and determine the output evaluation structure of 1 to 10,based on operating capacity,and establishes a three layer structure, seven input, one output of neural network, and improves activation functionand,adds momentum factor in traditional BP algorithm and sets to the learning rate of 0.05, the maximum number of training for 10000, the error of 10-2. This article comes true the evaluation research on location of bank outlets location, based on BP neural network and using vc + + compiler platform and calling MATLAB.