Legally scored

Abstract

PurposeAchieving equal treatment of credit applicants has been a legitimate concern of legislators and the credit industry. However, measures taken to date in attempting to comply with anti‐discrimination laws arguably do not allow for the most effective use of credit scoring models, and could run counter‐intuitive to the intention of legislation through indirect discrimination. The purpose of this paper is to offer an alternative interpretation that preserves the intention of legislation and also retains the integrity and effectiveness of credit scoring models.Design/methodology/approachThe paper makes a legal analysis of anti‐discrimination laws in the UK, with US law as a comparison, aiming to demonstrate that concerns in using information protected under anti‐discrimination laws as variables may be misplaced, because nothing in these laws precludes the inclusion of all relevant variables in modelling.FindingsThe inclusion of variables representing protected characteristics in credit scoring models may not contradict current anti‐discrimination laws.Research limitations/implicationsLimitations exist from the perspectives of customer relationship and the need for further checks and balances. Conclusive validation of the findings will need to come from the courts. The paper provides a springboard for empirical research on whether the inclusion of variables representing protected characteristics in credit scorecards continues to produce better decision‐making models.Practical implicationsThe findings benefit credit risk modelling as a whole in facilitating the development of credit scorecards that are in compliance with anti‐discrimination laws, without sacrificing their effectiveness.Originality/valueThe paper presents a fresh perspective and alternative solution to legal concerns regarding the use of protected characteristics in credit scoring, which will be useful to the credit industry.

A review of credit scoring research in the age of Big Data

“…These regulatory developments bring challenges to banks and credit bureaus, who used to be main owners of customers' accounts and financial payment data, as well as bring new opportunities to collaborate with fintechs, particularly alternative lending platforms [11]. Accordingly, the means through companies develop credit scoring systems by using Big Data has to be investigated thoroughly given this new paradigm shift, and more research is needed to develop more effective scorecards and more transparent algorithms that are in compliance with antidiscrimination laws and privacy rights on use of personal data (Ferretti, 2006;Chan and Seow, 2013;CFSI, 2015). Amoore and Piotukh (2015) discuss that Big Data analytics and algorithms are changing how we ingest data, how we partition it and finally how we act upon it through real-time analytics.…”

“…A main topic of interest has been on preventing discrimination in credit scoring. A recent stream of literature has studied: the effectiveness of anti-discrimination laws on preventing inclusion of the variables that represent protected features in credit models(Chan and Seow, 2013); developing regulatory oversight for fairness and accuracy of artificially intelligent scoring systems(Citron and Pasquale, 2014); and the impact of Big Data and associated algorithms on credit discrimination(Zarsky, 2014), governance(Campbell-Verduyn et al, 2017) and data privacy(Roderick, 2014).…”

The Law of Equal Opportunities or Unintended Consequences?: The Effect of Unisex Risk Assessment in Consumer Credit

“…Several studies (Fair, 1979;Johnson, 2004;Andreeva et al, 2004;Chan and Seow, 2013) have postulated certain implications from the prohibition but have not provided any empirical proof. One implication is that, if a prohibited variable is associated with default, its removal should lead to a reduction in predictive power, which should negatively impact on lenders through increased delinquency and cost of credit.…”