Multi-level credit risk prediction model based on deep learning
Ye Pang, Chunling Chen · 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering · 2022
In order to promote the application of deep neural network technology in the field of bank credit risk prediction and improve the prediction accuracy and efficiency of deep neural network in the field of bank credit risk prediction, a bank credit risk prediction model based on multi-level deep neural network is designed. By taking the weighted sum data of the customer characteristics obtained by the analytic hierarchy process as the input of the model, the coarse-grained screening is carried out by the h-net of the model. The customers whose credit evaluation is higher than the threshold are further screened by the L-net of the model, and finally the customer's credit score is output. The depth of credit risk can be predicted by neural network. The experiment on the real loan data of a commercial bank shows that the model has high prediction accuracy and efficiency.