Credibility modeling analysis of digital transformation of commercial banks in digital sector.

Chun Ye
Faculty of Management and Economics, Tianjin University, Tianjin,China,300072

Abstract:

In order to solve the problem of inaccurate evaluation results caused by high data dimension in credibility modeling analysis of digital transformation of commercial banks, a credibility modeling analysis method based on big data analysis is proposed. A generative countermeasure network is established. The generator and discriminator are used to balance the internal and external risk loss data, and the data are classified and processed. After preprocessing, the association rules of big data analysis are used to mine the classified data, and the feature vector after dimension reduction is obtained. Establish the credibility evaluation model of digital transformation of commercial banks, train the feature vector as the input data, and generate the evaluation results. The experimental results show that the recall rate, accuracy and F1 score of the proposed method are higher than those based on PCA, K-Means and GBDT, which has good evaluation effect.