Explaining Multi-Criteria Decision Aiding Models with an Extended Shapley Value

Explaining Multi-Criteria Decision Aiding Models with an Extended Shapley Value

Christophe Labreuche, Simon Fossier

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 331-339. https://doi.org/10.24963/ijcai.2018/46

The capability to explain the result of aggregation models to decision makers is key to reinforcing user trust. In practice, Multi-Criteria Decision Aiding models are often organized in a hierarchical way, based on a tree of criteria. We present an explanation approach usable with any hierarchical multi-criteria model, based on an influence index of each attribute on the decision. A set of desirable axioms are defined. We show that there is a unique index fulfilling these axioms. This new index is an extension of the Shapley value on trees. An efficient rewriting of this index, drastically reducing the computation time, is obtained. Finally, the use of the new index is illustrated on an example.
Keywords:
Knowledge Representation and Reasoning: Knowledge Representation and Decision ; Utility Theory
Knowledge Representation and Reasoning: Preference Modelling and Preference-Based Reasoning
Agent-based and Multi-agent Systems: Cooperative Games