An Application of Improved BP Neural Network in Personal Credit Scoring

Personal Credit Scoring is of great significance for commercial banks to circumvent credit consumption, the original BP algorithm´s convergence rate is slow, learning precision is low, the training process is easy to fall into local minimum, this paper presents an improved algorithm with variable learning rate based on BP algorithm, and applied to simulate personal credit scoring. After comparing we found the improved algorithm has greatly reduced the network´s number of iterations, shorten the network training time and improved the training accuracy.