Bagging Supervised Autoencoder Classifier for credit scoring

Automatic credit scoring, a crucial risk management tool for banks and financial institutes, has attracted much attention in the past few decades. As such, various approaches have been developed to accurately efficiently estimate defaults loan applicants seamlessly improve facilitate decision-making lending process. However, imbalanced nature of scoring datasets, as well heterogeneous features task pose many challenges developing implementing effective models, targeting generalization power classification models on unseen data. To mitigate these challenges, this paper, we propose Bagging Supervised Autoencoder Classifier (BSAC). BSAC is learning model which simultaneously leverages superior supervised autoencoders representation classification, mechanism handle irregularities feature space. autoencoder exploited learn an optimal latent space from perform top learned In particular, employed process construct samples original data tackle problem that arises Extensive experiments real-world benchmark datasets validate superiority robustness proposed method predicting outcome applications.