Portfolio Performance Attribution via Shapley Value

TL;DR

This paper advocates using Shapley value for performance attribution in investment portfolios, providing methods for exact and approximate computation, to fairly decompose performance among features and baseline.

Contribution

It introduces the application of Shapley value to portfolio performance attribution and discusses computational methods for practical implementation.

Findings

Shapley value offers a fair attribution method for investment features.

Exact and approximate computation methods are analyzed.

The approach improves attribution fairness over traditional methods.

Abstract

We consider an investment process that includes a number of features, each of which can be active or inactive. Our goal is to attribute or decompose an achieved performance to each of these features, plus a baseline value. There are many ways to do this, which lead to potentially different attributions in any specific case. We argue that a specific attribution method due to Shapley is the preferred method, and discuss methods that can be used to compute this attribution exactly, or when that is not practical, approximately.