Interpretable Credit Application Predictions With Counterfactual Explanations

Rory Mc Grath Luca Costabello Chan Le Van Paul Sweeney Farbod Kamiab Zhao Shen Freddy Lecue 1, 2
2 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : We predict credit applications with off-the-shelf, interchangeable black-box clas-sifiers and we explain single predictions with counterfactual explanations. Coun-terfactual explanations expose the minimal changes required on the input data to obtain a different result e.g., approved vs rejected application. Despite their effectiveness , counterfactuals are mainly designed for changing an undesired outcome of a prediction i.e. loan rejected. Counterfactuals, however, can be difficult to interpret , especially when a high number of features are involved in the explanation. Our contribution is twofold: i) we propose positive counterfactuals, i.e. we adapt counterfactual explanations to also explain accepted loan applications, and ii) we propose two weighting strategies to generate more interpretable counterfactuals. Experiments on the HELOC loan applications dataset show that our contribution outperforms the baseline counterfactual generation strategy, by leading to smaller and hence more interpretable counterfactuals.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.inria.fr/hal-01934915
Contributor : Freddy Lecue <>
Submitted on : Monday, November 26, 2018 - 1:01:16 PM
Last modification on : Thursday, November 29, 2018 - 1:19:55 AM
Document(s) archivé(s) le : Wednesday, February 27, 2019 - 2:26:35 PM

File

1811.05245.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01934915, version 1

Collections

Citation

Rory Mc Grath, Luca Costabello, Chan Le Van, Paul Sweeney, Farbod Kamiab, et al.. Interpretable Credit Application Predictions With Counterfactual Explanations. NIPS 2018 workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy, Dec 2018, Montreal, Canada. ⟨hal-01934915⟩

Share

Metrics

Record views

40

Files downloads

93