Logistic Regression or Neural Network? Which Provides Better Results for Retail Loans?

While there is extensive literature on the prediction of corporate bankruptcies, little classification retail borrowers. This also true in Hungary. Recognising who at risk becoming a bad debtor not easy. There are several ways to analyse data, which may yield different results. In this paper, my aim predict default household loans using logistic regression and neural networks. The question is, method produces better results?The analyses show that network model produced best most favourable accuracy was found be 81.5%.