Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 61 of the 63 references it cites were found in a registry or an index, and 2 are not checked yet.

Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning

Kaur, Harmanpreet, Nori, Harsha, Jenkins, Samuel, Caruana, Rich, Wallach, Hanna, Wortman Vaughan, Jennifer·2020·Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

Abstract

Machine learning (ML) models are now routinely deployed in domains ranging from criminal justice to healthcare. With this newfound ubiquity, ML has moved beyond academia and grown into an engineering discipline. To that end, interpretability tools have been designed to help data scientists and machine learning practitioners better understand how ML models work. However, there has been little evaluation of the extent to which these tools achieve this goal. We study data scientists' use of two existing interpretability tools, the InterpretML implementation of GAMs and the SHAP Python package. We conduct a contextual inquiry (N=11) and a survey (N=197) of data scientists to observe how they use interpretability tools to uncover common issues that arise when building and evaluating ML models. Our results indicate that data scientists over-trust and misuse interpretability tools. Furthermore, few of our participants were able to accurately describe the visualizations output by these tools. We highlight qualitative themes for data scientists' mental models of interpretability tools. We conclude with implications for researchers and tool designers, and contextualize our findings in the social science literature.

Overview

Integrity signals

Registry

Crossref · 10.1145/3313831.3376219

Cites

61 of 63 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

10 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 60 references

Research works printed but not linked: 13

  1. David Alvarez-Melis, Hal Daumé, III, Jennifer Wortman Vaughan, and Hanna Wallach. 2019. Weight of Evidence as a Basis for Human-Oriented Explanations. arXiv preprint arXiv:1910.13503 (2019). · arXiv
  2. Julia Angwin, Jeff Larson, Surya Mattu, and Kirchner Lauren. 2016. Machine Bias: There's software used across the country to predict future criminals. And it's biased against blacks. ProPublica, May 23 (2016), 2016. http://www.propublica.org/article/machine-bias-risk -assessments-in-criminal-sentencing
  3. 10.1007/978--3--540--30116--5_58 · doi:10.1007/978--3--540--30116--5_58
  4. Finale Doshi-Velez, Mason Kortz, Ryan Budish, Chris Bavitz, Sam Gershman, David O'Brien, Stuart Schieber, James Waldo, David Weinberger, and Alexandra Wood. 2017. Accountability of AI under the law: The role of explanation. arXiv preprint arXiv:1711.01134 (2017). · arXiv
  5. 10.1016/s0166--4115(08)62386--9 · doi:10.1016/s0166--4115(08)62386--9
  6. Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016). · arXiv
  7. Scott M Lundberg, Gabriel G Erion, and Su-In Lee. 2018. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018). · arXiv
  8. Prashan Madumal, Tim Miller, Frank Vetere, and Liz Sonenberg. 2018. Towards a Grounded Dialog Model for Explainable Artificial Intelligence. In First international workshop on socio-cognitive systems at IJCAI 2018. https://arxiv.org/abs/1806.08055 · arXiv
  9. Tim Miller. 2018. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence (2018).
  10. Harsha Nori, Samuel Jenkins, Paul Koch, and Rich Caruana. 2019. InterpretML: A Unified Framework for Machine Learning Interpretability. arXiv preprint arXiv:1909.09223 (2019). · arXiv
  11. Forough Poursabzi-Sangdeh, Daniel G Goldstein, Jake M Hofman, Jennifer Wortman Vaughan, and Hanna Wallach. 2018. Manipulating and measuring model interpretability. arXiv preprint arXiv:1802.07810 (2018). · arXiv
  12. Sarah Tan, Rich Caruana, Giles Hooker, Paul Koch, and Albert Gordo. 2018. Learning global additive explanations for neural nets using model distillation. arXiv preprint arXiv:1801.08640 (2018). · arXiv
  13. Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece, and Supriyo Chakraborty. 2018. Interpretable to whom? A role-based model for analyzing interpretable machine learning systems. arXiv preprint arXiv:1806.07552 (2018). · arXiv

Cited by

See all 668

Metadata

Authors
Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., & Wortman Vaughan, J.
Affiliations
  • University of Michigan (US)
  • Microsoft (United States) (US)
  • Microsoft Research New York City (United States) (US)
  • Microsoft Research, New York, NY, USA
Venue
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Publisher
ACM
Published
2020-04-21
Pages
1-14
OpenAlex
W3016099278
Cited by
564
References
60
Citations by year
2026: 77 · 2025: 83 · 2024: 96 · 2023: 88 · 2022: 104 · 2021: 88 · 2020: 26
FWCI
29.22
Type
conference paper
Language
en
Open access
closed
Locations
CHI Conference on Human Factors in Computing Systems (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
Keywords
model interpretability, data scientists, SHAP, generalized additive models, tool misuse, mental models, visualization comprehension, tool design, contextual inquiry

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning. https://app.cochat.ai/papers/10.1145/3313831.3376219
The paper
Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., & Wortman Vaughan, J. (2020). Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3313831.3376219

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.