Axiomatic Attribution for Multilinear Functions

Authors:
  • YSYi Sun
    Yi Sun
  • MSMukund Sundararajan
    Mukund Sundararajan

Abstract
We study the attribution problem, that is, the problem of attributing a change in the value of a characteristic function to its independent variables. We make three contributions. First, we propose a formalization of the problem based on a standard cost sharing model. Second, in our most important technical contribution, we show that there is a unique path attribution method that satisfies Affine Scale Invariance and Anonymity if and only if the characteristic function is multilinear. We term this the Aumann-Shapley-Shubik method. Third, we study multilinear characteristic functions in detail; we describe a computationally efficient implementation of the Aumann-Shapley-Shubik method and discuss practical applications to pay-per-click advertising and portfolio analysis.