Data-driven Multiperiod Robust Mean-Variance Optimization

TL;DR

This paper introduces a data-driven approach to multiperiod robust mean-variance portfolio optimization using Wasserstein balls to account for model uncertainty, with promising simulation results on US stock data.

Contribution

It proposes a novel multiperiod robust optimization framework based on Wasserstein ambiguity sets, integrating empirical data to determine uncertainty radius.

Findings

Outperforms popular strategies in US stock market simulations

Demonstrates robustness to model misspecification

Provides a practical method for dynamic portfolio management

Abstract

We study robust mean-variance optimization in multiperiod portfolio selection by allowing the true probability measure to be inside a Wasserstein ball centered at the empirical probability measure. Given the confidence level, the radius of the Wasserstein ball is determined by the empirical data. The numerical simulations of the US stock market provide a promising result compared to other popular strategies.