Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach

Presently, the use of a credit card has become an integral part contemporary banking and financial system. Predicting potential defaulters or debtors is crucial business opportunity for institutions. For now, some machine learning methods have been applied to achieve this task. However, with dynamic imbalanced nature default data, it challenging classical algorithms proffer robust models optimal performance. Research shown that performance can be significantly improved when provided features. In paper, we propose unsupervised feature method improve various classifiers using stacked sparse autoencoder (SSAE). The SSAE was optimized proposed learned excellent representations were used train classifiers. approach compared instance where trained raw data. Also, comparison made previous scholarly works, showed superior over other methods.