Bound and Collapse Bayesian Reject Inference for Credit Scoring - Archive ouverte HAL Access content directly
Reports Year :

Bound and Collapse Bayesian Reject Inference for Credit Scoring

(1) , (2)
1
2

Abstract

Reject inference is a method for inferring how a rejected credit applicant would have behaved had credit been granted. Credit-quality data on rejected applicants are usually missing not at random (MNAR). In order to infer credit-quality data MNAR, we propose a flexible method to generate the probability of missingness within a model-based bound and collapse Bayesian technique. We tested the method's performance relative to traditional reject-inference methods using real data. Results show that our method improves the classification power of credit scoring models under MNAR conditions.
Not file

Dates and versions

hal-00655036 , version 1 (25-12-2011)

Identifiers

  • HAL Id : hal-00655036 , version 1

Cite

Thomas B. Astebro, Gongyue Chen. Bound and Collapse Bayesian Reject Inference for Credit Scoring. 2010. ⟨hal-00655036⟩

Collections

HEC CNRS LARA
100 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More