Loan Prepayment Prediction Based on SVM-RFE and XGBoost Models

Abstract

The problem of large dimensionality of loan data and unbalanced data samples severely affects the classification, and the article proposes a support vector machine for feature recursive elimination and XGBoost for a loan early repayment prediction. Firstly, the combination of Pearson index and SVM-RFE in the data feature layer can reduce the dimension of data, find the best feature subset including more information, and then find more information. Secondly, the weighted cross-entropy loss function is introduced into the XGBoost algorithm to solve the problem of data imbalance. Finally, a comparative experiment is carried out on the LendingClub data set to confirm the effectiveness of the proposed model in predicting and analyzing the personal behavior of loan prepayment.