Sparse Mean-Variance Portfolios: A Penalized Utility Approach

TL;DR

This paper introduces a Bayesian approach for constructing sparse mean-variance portfolios that account for return uncertainty, enabling investors to select a small, effective set of assets.

Contribution

It proposes a novel penalized utility method for sparse portfolio optimization under uncertainty, applicable to both static and dynamic return models.

Findings

Effective sparse portfolios can be constructed using the proposed Bayesian penalized utility approach.

The method performs well in both static and dynamic asset return models.

Portfolio sparsity improves interpretability and potentially reduces transaction costs.

Abstract

This paper considers mean-variance optimization under uncertainty, specifically when one desires a sparsified set of optimal portfolio weights. From the standpoint of a Bayesian investor, our approach produces a small portfolio from many potential assets while acknowledging uncertainty in asset returns and parameter estimates. We demonstrate the procedure using static and dynamic models for asset returns.