Fairness and Discrimination in Lending Decisions : Multiple Protected Characteristics Analysis
Jain, Kushagra and Bowden, James and Cummins, Mark (2024) Fairness and Discrimination in Lending Decisions : Multiple Protected Characteristics Analysis. University of Strathclyde, Glasgow.
Preview |
Text.
Filename: Jain-etal-FinTech-2024-Fairness-and-discrimination-in-lending-decisions-multiple-protected.pdf
Final Published Version License: Download (1MB)| Preview |
Abstract
We build upon the comprehensive toolbox developed in Jain, Bowden and Cummins (2024), extending its applicability to multiple protected characteristics. We explore a way in which several characteristics can be simultaneously considered for multi-dimensional fairness promotion and potential mitigation of plausibly discriminatory practices. In the spirit of Jain, Bowden and Cummins (2024), once again we do this with a particular focus on US home mortgage loan applications with a granular public dataset. Finally, we address a prior deficiency, namely a worse overall model accuracy/performance as measured by Area Under the Curve (AUC). The improved AUC can be attributed to a better True Positive Rate of correctly classified loan acceptances, which is achieved with the aid of hyperparameter tuning. Specifically, we use Stratified K-Fold Cross-Validation combined with overfitting-robust hyperparameter tuning facilitated with the aid of a Grid Search. These were discussed but not explicitly implemented in the use case of Jain, Bowden and Cummins (2024). We document that even a narrow set and range of hyperparameters (mitigating the computational cost of employing the Grid Search) is sufficient to elicit these improvements. Lastly, we provide recommendations on the implications of our results including where a human-in-the-loop intervention may be merited for potentially enhancing fairness in such decision making.
ORCID iDs
Jain, Kushagra, Bowden, James ORCID: https://orcid.org/0000-0002-0419-1882 and Cummins, Mark ORCID: https://orcid.org/0000-0002-3539-8843;Persistent Identifier
https://doi.org/10.17868/strath.00091083-
-
Item type: Report ID code: 91083 Dates: DateEvent6 November 2024Published31 August 2024AcceptedSubjects: Social Sciences > Finance
Science > Mathematics > Electronic computers. Computer scienceDepartment: Strathclyde Business School > Accounting and Finance Depositing user: Pure Administrator Date deposited: 06 Nov 2024 11:32 Last modified: 11 Nov 2024 15:58 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/91083