Applying machine learning algorithms to predict default probability in the online credit market: Evidence from China

Abstract

Using data from Renrendai and three machine learning algorithms, namely, k-nearest neighbor, support vector machine, and random forest, we predicted the default probability of online loan borrowers and compared their prediction performance with that of a logistic model. The results show that, first, based on the AUC (area under the ROC curve) value, accuracy rate and Brier score, the machine learning models can accurately predict the default risk of online borrowers. Second, the integrated discrimination improvement (IDI) test results show that the prediction performance of the machine learning algorithms is significantly better than that of the logistic model. Third, after constructing the investor profit function with misclassification cost, we find that the machine learning algorithms can provide more benefits to investors.