Weber, Thomas A.Chehrazi, N.2012-11-072012-11-072012-11-072012https://infoscience.epfl.ch/handle/20.500.14299/86711This 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.account valuationconsumer creditcollectability scoringcredit collectionsmaximum-likelihood estimationself-exciting point processtext::working paper