The effect of introducing economic variables into credit scorecards: an example from invoice discounting

Jie Zhang and Lyn C. Thomas

Abstract

ABSTRACT

We demonstrate how introducing economic variables into a credit scorecard improves the predictive power of that scorecard. Such a scorecard can forecast default rates accurately, even when economic conditions change. This means we can develop a single-step approach to estimate the point-in-time probabilities of default (PDs), which are required by the Basel Accords' banking regulations. A one-step approach has several advantages over the more standard approach, which involves first estimating scores with no economic variables, then segmenting the portfolio by score bands and estimating the PD per segment. To build such a scorecard, we decompose it into the population odds and weights of evidence.We show that economic variables model the dynamics of the population odds part of the scorecard, which leads to an improvement in prediction. We then apply this extension to credit scoring to a real problem in invoice discounting. This is when banks lend to small businesses using the invoices that the businesses have issued as collateral. There is a significant volume of such lending, but it is not often addressed in the literature. The scorecards used to assess the risk of default of such small businesses are very similar to the behavioral scorecards used to assess default risk in lending to consumers. The results show that modeling the population odds by economic variables is very effective, but there is little improvement in the scorecard's performance if we model the dynamics of the weights of evidence by adding interactions between the economic variables and the performance characteristics of the borrowing firm.