Can reject inference ever work

By David J. Hand, W. Henley. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Characterizing Fairness Over the Set of Good Models Under Selective Labels (2021, background): “There is considerable debate as to the performance improvements of reject inference over simply training a model on the observed population, but reject inference methods remain popular in credit scoring settings [38, 39, 32, 33].”
Inferring the outcomes of rejected loans: an application of semisupervised clustering (2019, background): “However, most ﬁnancial institutions cannot afford the costs of the additional information from highly risky consumers (Hand and Henley, 1993).”
A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers (2000, background): “Secondly, instead of seeking to minimise the percentage of consumers who default, companies are hoping they can identify the customers who are most profitable.”
Deep generative models for reject inference in credit scoring (2019, background): “According to [6], reject inference represents several challenges.”
Does reject inference really improve the performance of application scoring models (2004, methodology): “…(Joanes, 1993/4), bivariate probit (Boyes et al., 1989), ‘‘parcelling’’, use of the EM algorithm (Demster et al., 1977), using a multinomial logistic model (Reichert et al., 1983), and collecting repayment performance data for rejects (Hand and Henley, 1993/4; Ash and Meester, 2002).”
Statistical Classification Methods in Consumer Credit Scoring: a Review (1997, background): “Hand and Henley (1993, 1994) have explored reject inference in detail.”
A rule of thumb for reject inference in credit scoring (2014, background): “Reject inference [2] attempts to address this kind of reject bias by estimating how rejected applicants would have performed had they been accepted.”