Innovation in Corporate Credit Scoring: Z-Score Optimization
21 Pages Posted: 26 Nov 2011
Date Written: November 22, 2011
This paper applies novel concepts from consumer credit scoring to corporate credit scoring. The literature of bankruptcy scoring and score combination and modeling is examined and financial ratios and combined credit score super scorecards are essentially interaction effects. An optimal credit score is built when these effects are properly specified and all predictive information in variables is extracted using a properly specified model. The fact that optimal credit scorecards can be built using interaction effects is show by superior performance of random forests out of the box as they include interaction effects in the model which are not included in logistic regression and trees unless explicitly specified. To build optimal scorecards one must detect and specify interaction effects of which financial ratios are simply one example or form. Random forests provide an invaluable tool to suggest variable interactions and in building optimal consumer and corporate scorecards.
Keywords: corporate credit scoring, optimal credit scoring, Altman Z-score, bankruptcy prediction, variable selection, combining credit scores, interaction effects, random forest, logistic regression, empirical vs. structural models
Suggested Citation: Suggested Citation