With the development of economic globalization and financial liberalization,\ncredit assessment plays an important role in maintaining the normal relationship\nof social economy. Personal credit assessment requires establishing\ncalibration models with statistic methods. The mono-method-based models\nare not capable to simultaneously hold the robustness, interpretation and prediction\naccuracy of the models. In this paper, back-propagation neural network\n(BPNN) was used to generate a new comprehensive variable for logistic\nregression (LR) by tuning the number of hidden nodes. The optimal backpropagation\nneural network-logistic regression combination model (BPNNLR)\nwas established with 5 input nodes, 7 hidden nodes and 1 output node.\nThe model performance was slightly improved. The prediction accuracy was\nraised up to 86.33% and 87.96% for the training samples and the test samples,\nrespectively. Results showed that the BPNN-LR model had higher classification\naccuracy than the LR model. It is concluded that the outcome performance\nprovides technical reference for the corporation�s decision making.
Loading....