Credit scoring, augmentation and lean models Export

@article{2005_BanasikCrook, abstract = {If a credit scoring model is built using only applicants who have been previously accepted for credit such a non-random sample selection may produce bias in the estimated model parameters and accordingly the model's predictions of repayment performance may not be optimal. Previous empirical research suggests that omission of rejected applicants has a detrimental impact on model estimation and prediction. This paper explores the extent to which, given the previous cutoff score applied to decide on accepted applicants, the number of included variables influences the efficacy of a commonly used reject inference technique, reweighting. The analysis benefits from the availability of a rare sample, where virtually no applicant was denied credit. The general indication is that the efficacy of reject inference is little influenced by either model leanness or interaction between model leanness and the rejection rate that determined the sample. However, there remains some hint that very lean models may benefit from reject inference where modelling is conducted on data characterized by a very high rate of applicant rejection.}, author = {Banasik, J. and Crook, J.}, citeulike-article-id = {649551}, citeulike-linkout-0 = {http://dx.doi.org/10.1057/palgrave.jors.2602017}, doi = {10.1057/palgrave.jors.2602017}, journal = {Journal of the Operational Research Society}, keywords = {augmentation, consumer, credit, reject-inference, scoring}, number = {9}, pages = {1072--1081}, posted-at = {2006-05-18 18:04:00}, priority = {0}, title = {Credit scoring, augmentation and lean models}, url = {http://dx.doi.org/10.1057/palgrave.jors.2602017}, volume = {56}, year = {2005} }

TY - JOUR ID - 2005_BanasikCrook L3 - citeulike-article-id:649551 N2 - If a credit scoring model is built using only applicants who have been previously accepted for credit such a non-random sample selection may produce bias in the estimated model parameters and accordingly the model's predictions of repayment performance may not be optimal. Previous empirical research suggests that omission of rejected applicants has a detrimental impact on model estimation and prediction. This paper explores the extent to which, given the previous cutoff score applied to decide on accepted applicants, the number of included variables influences the efficacy of a commonly used reject inference technique, reweighting. The analysis benefits from the availability of a rare sample, where virtually no applicant was denied credit. The general indication is that the efficacy of reject inference is little influenced by either model leanness or interaction between model leanness and the rejection rate that determined the sample. However, there remains some hint that very lean models may benefit from reject inference where modelling is conducted on data characterized by a very high rate of applicant rejection. IS - 9 JF - Journal of the Operational Research Society EP - 1081 TI - Credit scoring, augmentation and lean models VL - 56 SP - 1072 KW - augmentation KW - consumer KW - credit KW - reject-inference KW - scoring AU - Banasik, J AU - Crook, J PY - 2005/// UR - http://dx.doi.org/10.1057/palgrave.jors.2602017 ER -