Fair lending needs explainable models for responsible recommendation
arXiv:1809.04684
Abstract
The financial services industry has unique explainability and fairness challenges arising from compliance and ethical considerations in credit decisioning. These challenges complicate the use of model machine learning and artificial intelligence methods in business decision processes.
arXiv comment4 pages, position paper accepted for FATREC 2018 conference at ACM RecSys
Cited by in corpus (9)
- Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations
- Fairness-Aware Explainable Recommendation over Knowledge Graphs
- Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
- Counterfactual Learning on Graphs: A Survey
- Counterfactual Explanations for Arbitrary Regression Models
- Seven challenges for harmonizing explainability requirements
- Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
- Provable Multi-Objective Reinforcement Learning with Generative Models
- Ontology drift is a challenge for explainable data governance