A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing
1
H2O.ai, Mountain View, CA 94043, USA
2
Department of Decision Sciences, The George Washington University, Washington, DC 20052, USA
3
BLDS, LLC, Philadelphia, PA 19103, USA
*
Authors to whom correspondence should be addressed.
†
All authors contributed equally to this work.
Information 2020, 11(3), 137; https://doi.org/10.3390/info11030137
Received: 21 December 2019
/
Revised: 24 February 2020
/
Accepted: 25 February 2020
/
Published: 29 February 2020
(This article belongs to the Special Issue Machine Learning with Python)
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.
View Full-Text
Keywords:
deep learning; disparate impact; explanation; fairness; gradient boosting machine; interpretable; machine learning; neural network; Python
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Gill, N.; Hall, P.; Montgomery, K.; Schmidt, N. A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing. Information 2020, 11, 137. https://doi.org/10.3390/info11030137
AMA Style
Gill N, Hall P, Montgomery K, Schmidt N. A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing. Information. 2020; 11(3):137. https://doi.org/10.3390/info11030137
Chicago/Turabian StyleGill, Navdeep, Patrick Hall, Kim Montgomery, and Nicholas Schmidt. 2020. "A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing" Information 11, no. 3: 137. https://doi.org/10.3390/info11030137
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
