Interpretable Credit Application Predictions With Counterfactual Explanations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Interpretable Credit Application Predictions With Counterfactual Explanations


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.
Fichier principal
Vignette du fichier
1811.05245.pdf (262.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01934915 , version 1 (26-11-2018)


  • HAL Id : hal-01934915 , version 1


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⟩
213 View
874 Download


Gmail Facebook X LinkedIn More