Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Publication
Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This paper presents a model for the estimation of the repayment process of delinquent credit-card accounts conditional on account-specific and macroeconomic information. Based on this model we construct a dynamic collectability score (DCS). The DCS estimates the account-specific probability of collecting a given percentage of outstanding debt over a chosen time horizon. It also allows for account valuation and estimation of the future repayment frequency. The method is tested using a large set of account-level repayment data. The improvements in classification and prediction performance compared to standard bank-internal scoring methods are significant.
Luca Giovanni Pattaroni, Mischa-Sébastien Piraud, Letícia Cabeçadas Do Carmo
Vincent Kaufmann, Guillaume Simon Joseph Drevon, Alexis Gumy, Gil Viry, Florian Lucien Jacques Masse