Computer Science > Computer Science and Game Theory
Title:Stability Bands for Feature Attribution: The Core, the Nucleolus and the Bargaining Set of Explained-Variance Games
Abstract:Shapley-value attributions are the default way of explaining machine-learning predictions in economics, but they report a single number per feature and say nothing about whether a coalition of features that jointly accounts for more than it receives could contest that allocation. We study feature attribution through the core, the nucleolus and the bargaining set of an explained-variance game, in which the worth of a set of features is the variance of the model's predictions that those features generate. For every feature we report a stability band (its range of shares over the core, or over the least core when the core is empty), with the nucleolus as distinguished point and a certificate that the allocation admits no justified objection. Three results organise the approach. First, for linear models the game is exactly 2-additive, with pairwise Harsanyi dividends $2\beta_i\beta_j\sigma_{ij}$, so multicollinearity is what creates coalitional structure. Second, in every 2-additive game the prenucleolus coincides with the Shapley value, the (least) core is point-symmetric around it, and the core is non-empty if and only if every cut of the interaction graph has non-negative weight. The Shapley value thus always lies in the prebargaining set, and stability adds information only through band widths and interactions of order three or more. Third, for convex games the bands have a closed form and any allocation can be certified with one minimum cut. In a hedonic price model, the usual mean-SHAP explanation admits a justified objection by the coalition {Ratings, ROM, Battery}. In a gradient-boosting forecaster of retail orders the exact game has an empty core and strong higher-order interactions; the nucleolus departs from the Shapley value by up to 0.19 variance shares, and sparse third-order surrogates recover it where pairwise ones cannot.
| Comments: | Presented at the XXV Jornadas Latinoamericanas de Teoría Económica (JOLATE 2026), San Luis, Argentina, October 29, 2026. 24 pages, 5 figures |
|---|---|
| Subjects: | Computer Science and Game Theory (cs.GT) ; Machine Learning (cs.LG); Econometrics (econ.EM) |
| Cite as: | arXiv:2611.25238 [cs.GT] |
| (or arXiv:2611.25238v1 [cs.GT] for this version) | |
| https://doi.org/10.48550/arXiv.2611.25238 arXiv-issued DOI via DataCite (pending registration) |
Submission history
Access Paper:
- HTML (experimental)
Additional Features
- Audio Summary
Current browse context:
References & Citations
- Google Scholar
- Semantic Scholar
BibTeX formatted citation
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.