Fairness in credit scoring: assessment, implementation and profit implications
From MaRDI portal
Publication:2060424
Abstract: The rise of algorithmic decision-making has spawned much research on fair machine learning (ML). Financial institutions use ML for building risk scorecards that support a range of credit-related decisions. Yet, the literature on fair ML in credit scoring is scarce. The paper makes three contributions. First, we revisit statistical fairness criteria and examine their adequacy for credit scoring. Second, we catalog algorithmic options for incorporating fairness goals in the ML model development pipeline. Last, we empirically compare different fairness processors in a profit-oriented credit scoring context using real-world data. The empirical results substantiate the evaluation of fairness measures, identify suitable options to implement fair credit scoring, and clarify the profit-fairness trade-off in lending decisions. We find that multiple fairness criteria can be approximately satisfied at once and recommend separation as a proper criterion for measuring the fairness of a scorecard. We also find fair in-processors to deliver a good balance between profit and fairness and show that algorithmic discrimination can be reduced to a reasonable level at a relatively low cost. The codes corresponding to the paper are available on GitHub.
Recommendations
- Matching code and law: achieving algorithmic fairness with optimal transport
- FairDEA -- removing disparate impact from efficiency scores
- scientific article; zbMATH DE number 6866333
- scientific article; zbMATH DE number 7064055
- Countering racial discrimination in algorithmic lending: a case for model-agnostic interpretation methods
Cites work
- An algorithm for removing sensitive information: application to race-independent recidivism prediction
- Benchmarking state-of-the-art classification algorithms for credit scoring: an update of research
- Deep learning for credit scoring: do or don't?
- Development and application of consumer credit scoring models using profit-based classification measures
- scientific article; zbMATH DE number 6866333 (Why is no real title available?)
- Quantile regression for modelling distributions of profit and loss
- Recent developments in consumer credit risk assessment
- Reject inference, augmentation, and sample selection
Cited in
(31)- Achieving fair treatment in algorithmic classification
- Model-based and actual independence for fairness-aware classification
- How do fairness definitions fare? Testing public attitudes towards three algorithmic definitions of fairness in loan allocations
- Accuracy and fairness trade-offs in machine learning: a stochastic multi-objective approach
- Fairness in learning-based sequential decision algorithms: a survey
- Explainable models of credit losses
- FairDEA -- removing disparate impact from efficiency scores
- Credit offering strategy and dynamic pricing in the presence of consumer strategic behavior
- Leveraging integer linear programming to learn optimal fair rule lists
- Matching code and law: achieving algorithmic fairness with optimal transport
- Credit scoring with drift adaptation using local regions of competence
- scientific article; zbMATH DE number 6866333 (Why is no real title available?)
- Beyond submodularity: a unified framework of randomized set selection with group fairness constraints
- Bias, Fairness and Accountability with Artificial Intelligence and Machine Learning Algorithms
- A Joint Fairness Model with Applications to Risk Predictions for Underrepresented Populations
- Countering racial discrimination in algorithmic lending: a case for model-agnostic interpretation methods
- Causal Fairness Analysis: A Causal Toolkit for Fair Machine Learning
- Synthesizing Fair Decision Trees via Iterative Constraint Solving
- Supervised feature compression based on counterfactual analysis
- A Markovian score model for evaluating provider performance for continuity of care -- an explainable analytics approach
- On the impact of multi-dimensional local differential privacy on fairness
- Mitigating adversarial attacks on transformer models in credit scoring
- Differential quantile-based sensitivity in discontinuous models
- Interpretable machine learning and explainable artificial intelligence
- Counterfactual situation testing: from single to multidimensional discrimination
- Uplift modeling with continuous treatments: a predict-then-optimize approach
- On fair Lasso regression
- Sensitivity-based measures of discrimination in insurance pricing
- Credit risk modeling innovations in a changing world
- Fair models in credit: intersectional discrimination and the amplification of inequity
- Strong group fair classification via optimal transport and mixed-integer linear programming
This page was built for publication: Fairness in credit scoring: assessment, implementation and profit implications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2060424)
