A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681 · cited 1×
“• Model documentation: models cards [56], e.”
Goldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2014.907095 · Cited by 1,861 · cited 4×
“, inaccuracy in the presence of strong interactions and correlations [23,30].”
BackgroundResultInfluentialCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Visualizing the effects of predictor variables in black box supervised learning models
Apley, D. W., & Zhu, J. (2020) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/rssb.12377 · Cited by 1,535
Consistent Individualized Feature Attribution for Tree Ensembles
Lundberg, S. M., Erion, G. G., & Lee, S.-I. (2018) · arXiv · doi:10.48550/arxiv.1802.03888 · Cited by 1,430
Mitigating Unwanted Biases with Adversarial Learning
Zhang, B. H., Lemoine, B., & Mitchell, M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278779 · Cited by 1,387
Predictive learning via rule ensembles
Friedman, J. H., & Popescu, B. E. (2008) · The Annals of Applied Statistics · doi:10.1214/07-aoas148 · Cited by 1,315
Data preprocessing techniques for classification without discrimination
Kamiran, F., & Calders, T. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-011-0463-8 · Cited by 1,305
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Niu, F., Recht, B., Re, C., & Wright, S. J. (2011) · arXiv · doi:10.48550/arxiv.1106.5730 · Cited by 1,211 · cited 1×
“Because the unconstrained ML models, gradient boosting machines (GBMs, e.g., [13,14]) and artificial neural networks (ANNs, e.g., [15–18]), do not exhibit convincing accuracy benefits on the simulated or mortgage data and can also present the unmitigated risks discussed above, further explanation and…”
BackgroundFooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375830 · Cited by 900
Stealing Machine Learning Models via Prediction APIs
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016) · arXiv · doi:10.48550/arxiv.1609.02943 · Cited by 796
This Looks Like That: Deep Learning for Interpretable Image Recognition
Chen, C., Li, O., Tao, C., Barnett, A. J., Su, J., & Rudin, C. (2018) · arXiv · doi:10.48550/arxiv.1806.10574 · Cited by 702
Zafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · cited 1×
“Accuracy and other confusion matrix measures are also reported by demographic segment [28].”
BackgroundA comparative study of fairness-enhancing interventions in machine learning
Friedler, S. A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E. P., & Roth, D. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287589 · Cited by 601
Accurate intelligible models with pairwise interactions
Lou, Y., Caruana, R., Gehrke, J., & Hooker, G. (2013) · Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2487575.2487579 · Cited by 564 · cited 3×
“XNNs also bear a strong resemblance to generalized additive models (GAMs) and so-called explainable boosting machines (EBMs or GA2Ms), which consider main effects and a small number of two-way interactions and may also incorporate boosting into their training [14,29].”
BackgroundMethodScalable Private Learning with PATE
Papernot, N., Song, S., Mironov, I., Raghunathan, A., Talwar, K., & Erlingsson, Ú. (2018) · arXiv · doi:10.48550/arxiv.1802.08908 · Cited by 373
Decision Theory for Discrimination-Aware Classification
Kamiran, F., Karim, A., & Zhang, X. (2012) · 2012 IEEE 12th International Conference on Data Mining · doi:10.1109/icdm.2012.45 · Cited by 300
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Wallace, E., Tuyls, J., Wang, J., Subramanian, S., Gardner, M., & Singh, S. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations · doi:10.18653/v1/d19-3002 · Cited by 116 · cited 1×
“Post-hoc explanation : structured data explanations with alibi and PDPbox , image classification explanations with DeepExplain , and natural language explanations with allennlp [45–47].”
BackgroundFairwashing: the risk of rationalization
Aïvodji, U., Arai, H., Fortineau, O., Gambs, S., Hara, S., & Tapp, A. (2019) · arXiv · doi:10.48550/arxiv.1901.09749 · Cited by 54
Cited by
Towards a standard for identifying and managing bias in artificial intelligence
Schwartz, R., Vassilev, A., Greene, K., Perine, L., Burt, A., & Hall, P. (2022) · doi:10.6028/nist.sp.1270 · Cited by 548
“Modeling algorithms or debiasing techniques that rely on demographic information, as most pre-, in-, and postprocessing methods do, may pose higher risks in regulated environments where disparate treatment must be avoided [200].”
BackgroundSelf-citationŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 278
Financial Risk Management and Explainable, Trustworthy, Responsible AI
Fritz-Morgenthal, S., Hein, B., & Papenbrock, J. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.779799 · Cited by 147
“For a United States Fair Lending Perspective on Machine Learning (see Hall et al., 2021).”
BackgroundWatkins, E. A., McKenna, M., & Chen, J. (2022) · arXiv · doi:10.48550/arxiv.2202.09519 · Cited by 35
Watkins, E. A., & Chen, J. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658938 · Cited by 25
“H2O.ai offers a responsible ML workflow paper [25], which ac-knowledges that “it is not clear that the use of this [80”
Background
Metadata
- Authors
- Gill, N., Hall, P., Montgomery, K., & Schmidt, N.
- Venue
- Information
- Publisher
- MDPI AG
- Published
- 2020-02-29
- Volume
- 11
- Issue
- 3
- Pages
- 137
- ISSN
- 2078-2489 (ISSN-L)
- OpenAlex
- W3010319796
- Cited by
- 36
- References
- 21
- FWCI
- 1.99
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.