Explainable Shapley-Based Allocation (Student Abstract)

The Shapley value is one of the most important normative division scheme in cooperative game theory, satisfying basic axioms. However, some allocation according to may seem unfair humans. In this paper, we develop an automatic method that generates intuitive explanations for a Shapley-based payoff allocation, which utilizes Given coalitional game, our decomposes it sub-games, easy generate verbal explanations, and shows given composed sub-games. Since each sub-game perceived as fair, should fair well. We run experiment with 210 human participants show when applying method, humans perceive significantly more than using general standard explanation.