EconBase
← All papers

Explaining black box decisions by Shapley cohort refinement

Masayoshi Mase, Art B. Owen, Benjamin Seiler

arXiv 1 Nov 2019 · Machine Learning · 30 citations (OpenAlex)

arXiv:1911.00467 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We introduce a variable importance measure to quantify the impact of individual input variables to a black box function. Our measure is based on the Shapley value from cooperative game theory. Many measures of variable importance operate by changing some predictor values with others held fixed, potentially creating unlikely or even logically impossible combinations. Our cohort Shapley measure uses only observed data points. Instead of changing the value of a predictor we include or exclude subjects similar to the target subject on that predictor to form a similarity cohort. Then we apply Shapley value to the cohort averages. We connect variable importance measures from explainable AI to function decompositions from global sensitivity analysis. We introduce a squared cohort Shapley value that splits previously studied Shapley effects over subjects, consistent with a Shapley axiom.

Citation extraction

27
references
56
in-text mentions
27
distinct cited
4
self-citations
6,887
main-text words

appendix boundary found by appendix_titled_section at “Appendix 1 Approach of \citet{stru:kono:2010}” · 74% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Kumar, I. E., Venkatasubramanian, S., Scheidegger, C., and Friedler, S (2020) Problems with Shapley-value-based explanations as feature importance measures1.00063100%
2Sundararajan, M. and Najmi, A (2020) The many Shapley values for model explanation0.87472100%
3Lundberg, S. M. and Lee, S.-I (2017) A unified approach to interpreting model predictions0.87452100%
4Strumbelj, E. and Kononenko, I (2010) An efficient explanation of individual classifications using game theory0.8558462%
5Song, E., Nelson, B. L., and Staum, J (2016) Shapley effects for global sensitivity analysis: Theory and computation0.84333100%
6Owen, A. B (2014) Sobol' indices and Shapley value self0.64422100%
7Shapley, L. S (1952) A value for n-person games0.64422100%
8Kuo, F., Sloan, I., Wasilkowski, G., and Woźniakowski, H (2010) On decompositions of multivariate functions0.51121100%
9Sobol', I. M (1969) Multidimensional Quadrature Formulas and Haar Functions0.51121100%
10Strumbelj, E. and Kononenko, I (2014) Explaining prediction models and individual predictions with feature contributions0.51121100%

Showing the top 10 of 27 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Cohort Shapley value for algorithmic fairness0.92843
2Variable importance without impossible data0.84333