Research and Application of PSO-BP Neural Networks in Credit Risk Assessment

According to the complexity of financial system, the model of credit risk assessment based on PSO algorithm and BP neural network integrated is proposed, which in order to improve the accuracy and reliability of risk assessment. First the neural network model of a credit risk evaluation is created, and then PSO algorithm is introduced to optimize the weight and threshold of the neural network, at last, using the indexes and regarding relevant data of 250 enterprises as sample, the BP neural network is trained and tested. Compared with the traditional calculation methods, experimental results show that the method is a feasible and effective assessment method with fast convergence and high precision prediction.