Ensemble Learning or Deep Learning? Application to Default Risk Analysis

Proper credit risk management is essential for lending institutions as substantial losses can be incurred when borrowers default. Consequently, statistical methods that can measure and analyze credit risk objectively are becoming increasing important. This study analyzed default payment data from Taiwan and compared the prediction accuracy and classification ability of three ensemble learning methods-specifically, Bagging, Random Forest, and Boosting-with those of various neural network methods, each of which has a different activation function. The results indicate that Boosting has a high prediction accuracy, whereas that of Bagging and Random Forest is relatively low. They also indicate that the prediction accuracy and classification performance of Boosting is better than that of deep neural networks, Bagging, and Random Forest.