Scoring decisions in the context of economic uncertainty
- 14 Downloads
We consider methods for incorporating forecasts of future economic conditions into acquisition decisions for scored retail credit and loan portfolios. We suppose that a portfolio manager is faced with two possible future economic scenarios, each characterised by a known probability of occurrence and by known performance functions that give expected profit and volume. We suppose further that he must choose in advance the scoring strategy and score cutoffs to optimise performance. We show that, despite the uncertainty of performance induced by economic conditions, every efficient policy consists of a single cutoff, provided the expected profit and volume performance curves in each scenario are concave. If these curves are not concave, efficient operating points can be characterised as cutoffs on a redefined score. In cases in which two scorecards are available, we show that it may be advantageous to randomly choose the scorecard to be employed, and we provide methods for selecting efficient operating points. Discussion is limited to cases with two scorecards and two economic scenarios, but our approach and results generalise to more scorecards and more economic scenarios.
Keywordsportfolio optimisation decision-making under risk risk measures economic forecasts
The authors are grateful to the anonymous reviewers, who provided many helpful comments and suggestions for improvement, particularly with regard to variance derivations included in the original draft.
- Bellotti T and Crook JN (2007). Credit scoring with macroeconomic variables. Proceedings of Credit Scoring and Credit Control Conference X. Edinburgh University: Edinburgh, UK.Google Scholar
- De Andrade FWM and Silva RG (2007). Use of macro-economic factors in credit scoring—application to point-in-time risk evaluation of SMEs. Proceedings of Credit Scoring and Credit Control Conference X. Edinburgh University: Edinburgh, UK.Google Scholar
- Gao L (2008). Loan origination decision based on multiple scores with application to installment loan portfolio selection. PhD Dissertation, University of Virginia.Google Scholar
- Hoadley B and Oliver RM (1998). Business measures of scorecard benefit . IMA J Math Appl to Bus Ind 9: 55–64.Google Scholar
- Lewis EM (1992). An Introduction to Credit Scoring . Fair Isaac and Co.: San Rafael, California.Google Scholar
- Overstreet GA, Bradley EL and Kemp RS (1992). The flat-maximum effect and generic linear scoring models: A test . IMA J Math Appl Bus Ind 4: 97–109.Google Scholar
- Scott MJJ, Niranjan M, Melvin DG and Prager RW (1998). Maximum realisable performance: A principled method for enhancing performance by using multiple classifiers in variable cost problem domains. Technical Report CUED/F-INFENG/TR.320, University of Cambridge.Google Scholar
- Zandi M (1998). Incorporating economic information into credit risk underwriting. In: Mays E (ed). Credit Risk Modeling. Glenlake Publishing Chicago, pp 155–168.Google Scholar