# The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory

@article{Merrick2019TheEG, title={The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory}, author={Luke Merrick and Ankur Taly}, journal={ArXiv}, year={2019}, volume={abs/1909.08128} }

Recently, a number of techniques have been proposed to explain a machine learning (ML) model's prediction by attributing it to the corresponding input features. Popular among these are techniques that apply the Shapley value method from cooperative game theory. While existing papers focus on the axiomatic motivation of Shapley values, and efficient techniques for computing them, they do not justify the game formulations used. For instance, we find that the SHAP algorithm's formulation (Lundberg… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

#### Citations

##### Publications citing this paper.

## Problems with Shapley-value-based explanations as feature importance measures

VIEW 5 EXCERPTS

CITES BACKGROUND & METHODS

HIGHLY INFLUENCED

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 21 REFERENCES

## A Unified Approach to Interpreting Model Predictions

VIEW 14 EXCERPTS

HIGHLY INFLUENTIAL

## Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems

VIEW 7 EXCERPTS

HIGHLY INFLUENTIAL

## An Efficient Explanation of Individual Classifications using Game Theory

VIEW 8 EXCERPTS

HIGHLY INFLUENTIAL

## Norm Theory: Comparing Reality to Its Alternatives.

VIEW 5 EXCERPTS

HIGHLY INFLUENTIAL

## Consistent Individualized Feature Attribution for Tree Ensembles

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## The many Shapley values for model explanation

VIEW 2 EXCERPTS