Data Analytics in Financial Portfolio Recovery Management

Abstract

Financial inclusion is a social need that is gaining more and more strength in developing countries. Microcredit is an effective way to enable financial inclusion, but it represents a challenge in portfolio management. This work applies data analytics and machine learning techniques to predict the behavior of the loan default in a non-financial entity. Decision trees have shown the best prediction performance to determine whether a loan will be paid or become irrecoverable after running five predictive models.