Information · 2020 · 34 citations · 35 references
ComputingComputer ScienceData ScienceDiscriminationMachine LearningStatistical LearningAlgorithmic FairnessDeep LearningDisparate ImpactExplainable Machine LearningFairness In Machine LearningRepresentation LearningFeature ImportanceGroup FairnessInterpretabilityInterpretable ModelingIntrinsic InterpretabilityModel InterpretabilityPost Hoc ExplanationsTransparency
This manuscript outlines a viable approach for training and evaluating machine learning systems for high-stakes, human-centered, or regulated applications using common Python programming tools. The accuracy and intrinsic interpretability of two types of constrained models, monotonic gradient boosting machines and explainable neural networks, a deep learning architecture well-suited for structured data, are assessed on simulated data and publicly available mortgage data. For maximum transparency and the potential generation of personalized adverse action notices, the constrained models are analyzed using post-hoc explanation techniques including plots of partial dependence and individual conditional expectation and with global and local Shapley feature importance. The constrained model predictions are also tested for disparate impact and other types of discrimination using measures with long-standing legal precedents, adverse impact ratio, marginal effect, and standardized mean difference, along with straightforward group fairness measures. By combining interpretable models, post-hoc explanations, and discrimination testing with accessible software tools, this text aims to provide a template workflow for machine learning applications that require high accuracy and interpretability and that mitigate risks of discrimination.
35
Jacob Cohen · Psychological Bulletin · 1992 · 42.2K citations
Greedy function approximation: A gradient boosting machine.
Jerome H. Friedman · The Annals of Statistics · 2001 · 29K citations · Full text
Multivariate Adaptive Regression Splines
Jerome H. Friedman · The Annals of Statistics · 1991 · 8.1K citations · Full text
A Unified Approach to Interpreting Model Predictions
Scott Lundberg, Su‐In Lee · arXiv (Cornell University) · 2017 · 7.6K citations · Full text
Deep Learning with Differential Privacy
Martı́n Abadi, Andy Chu, Ian Goodfellow et al. · 2016 · 5.9K citations · Full text