Machine Learning Meets Markowitz

← Back to all papers

6.8 / 10 NBER Text Methods

Authors: Yijie Wang, Hao Gao, Campbell R. Harvey, Yan Liu, Xinyuan Tao

Published: 2026-02-25 · View on NBER · PDF

---

Abstract

The standard approach to portfolio selection involves two stages: forecast the asset returns and then plug them into an optimizer. We argue that this separation is deeply problematic. The first stage treats cross-sectional prediction errors as equally important across all securities. However, given

---

NoteAnalysis Pending

This paper has been relevance-scored (6.8/10). Full analysis is generated for papers scoring ≥ 7.5.