The DOI matches its Crossref record; 63 of the 64 references it cites were found in a registry or an index.
Shapley Values for Feature Selection: The Good, the Bad, and the Axioms
Open accessAbstract
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for attribution in transferable utility games. The Shapley value is provably the only solution concept satisfying these axioms. In this paper, we introduce the Shapley value and draw attention to its recent uses as a feature selection tool. We call into question this use of the Shapley value, using simple, abstract “toy” counterexamples to illustrate that the axioms may work against the goals of feature selection. From this, we develop a number of insights that are then investigated in concrete simulation settings, with a variety of Shapley value formulations, including SHapley Additive exPlanations (SHAP) and Shapley Additive Global importancE (SAGE). The aim is not to encourage any use of the Shapley value for feature selection, but we aim to clarify various limitations around their current use in the literature. In so doing, we hope to help demystify certain aspects of the Shapley value axioms that are viewed as “favourable”. In particular, we wish to highlight that the favourability of the axioms depends non-trivially on the way in which the Shapley value is appropriated in the XAI application.
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.
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?
The cited source says what the claim attributes to it.
In the citing paper
“we incorporated the use of interpretability tools (eg, SHAP 28 values, feature importance) to ensure transparency, a priority emphasized in recent ML reporting guidelines.”
From Linguistic markers for identifying post-traumatic stress disorder and associated symptoms: a systematic literature review (2025) · cites this paper as [28]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“To align with best practices 27 for systematic reviews of ML studies, we augmented PROBAST with criteria tailored to these challenges”
From Linguistic markers for identifying post-traumatic stress disorder and associated symptoms: a systematic literature review (2025) · cites this paper as [28]
Experimental — accuracy not yet measured
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
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
From local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551
17. A Value for n-Person Games
Shapley, L. S. (1953) · Contributions to the Theory of Games (AM-28), Volume II · doi:10.1515/9781400881970-018 · Cited by 6,950
A survey on feature selection methods
Chandrashekar, G., & Sahin, F. (2014) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2013.11.024 · Cited by 5,189
Shapley, L. S. (1988) · The Shapley Value · doi:10.1017/cbo9780511528446.003 · Cited by 4,954
Explaining prediction models and individual predictions with feature contributions
Štrumbelj, E., & Kononenko, I. (2014) · Knowledge and Information Systems · doi:10.1007/s10115-013-0679-x · Cited by 2,286
Tukey, J. W. (1962) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177704711 · Cited by 1,860
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
Budescu, D. V. (1993) · Psychological Bulletin · doi:10.1037/0033-2909.114.3.542 · Cited by 1,193
Research works printed but not linked: 1
- claeskens, 2008, Model Selection Model Averaging
Cited by
The Shapley Value in Machine Learning
Rozemberczki, B., Watson, L., Bayer, P., Yang, H.-T., Kiss, O., Nilsson, S., & Sarkar, R. (2022) · Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/778 · Cited by 296
The Shapley Value in Machine Learning
Rozemberczki, B., Watson, L., Bayer, P., Yang, H.-T., Kiss, O., Nilsson, S., & Sarkar, R. (2022) · arXiv · doi:10.48550/arxiv.2202.05594 · Cited by 312
“The feature selection game treats input features of a machine learning model as players and model performance as the payoff [Guyon et al. , 2003; Fryer et al. , 2021 Shapley values, and close relatives such as the Banzhaf index III, 1964 ] , have been studied as a measure of feature importance in…”
Methodvan Zyl, C., Ye, X., & Naidoo, R. (2024) · Applied Energy · doi:10.1016/j.apenergy.2023.122079 · Cited by 248
Nwakanma, C. I., Ahakonye, L. A. C., Njoku, J. N., Odirichukwu, J. C., Okolie, S. A., Uzondu, C., Ndubuisi Nweke, C. C., & Kim, D.-S. (2023) · Applied Sciences · doi:10.3390/app13031252 · Cited by 202
Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions
Theissler, A., Spinnato, F., Schlegel, U., & Guidotti, R. (2022) · IEEE Access · doi:10.1109/access.2022.3207765 · Cited by 194
Metadata
- Authors
- Fryer, D., Strumke, I., & Nguyen, H.
- Affiliations
- The University of Queensland (AU)
- La Trobe University (AU)
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 144352-144360
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3131037858
- Semantic Scholar
- 6573fa74af238d1e3538c026997e31b9f67f19f7
- Cited by
- 347
- References
- 64
- Citations by year
- 2026: 56 · 2025: 102 · 2024: 86 · 2023: 58 · 2022: 34 · 2021: 11
- FWCI
- 16.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- arXiv (Cornell University)
- La Trobe University (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Game Theory and Voting Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- Shapley value, feature selection, explainable AI, axioms, SHAP, sage, counterexample, transferable utility games, attribution
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: Shapley Values for Feature Selection: The Good, the Bad, and the Axioms. https://app.cochat.ai/papers/10.1109/access.2021.3119110
- The paper
- Fryer, D., Strumke, I., & Nguyen, H. (2021). Shapley Values for Feature Selection: The Good, the Bad, and the Axioms. IEEE Access. https://doi.org/10.1109/access.2021.3119110
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.