Study on the Prediction of Imbalanced Bank Customer Churn Based on Generative Adversarial Network

Abstract

The imbalanced commercial bank customer data will lead to the unpredictability of the minority class. Therefore, this paper proposes an imbalanced data method based on generative adversarial network to deal the problem of poor prediction performance of traditional classifiers for minority class. This paper method is based on the generative adversarial network to generate minority class samples to improve imbalanced data. Finally, the classifier is used to train the balanced data to improve the prediction performance of minority class. In this experiment, the data of a commercial bank customer were measured with indicators such as F1, Precision, and compared with traditional data sampling methods such as SMOTE, BSSMOTE. This method is feasible and applicable to the classification of imbalanced data of banks by observing the experimental results, which has better application value.