We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Equity Factor Timing: A Two-Stage Machine Learning Approach.
- Authors
DiCiurcio, Kevin J.; Wu, Boyu; Xu, Fei; Rodemer, Scott; Wang, Qian
- Abstract
This article discusses the importance of incorporating market conditions and macroeconomic factors in factor investing strategies. It explores the potential benefits of factor timing, which involves shifting exposure to different factors based on their expected performance. The authors propose a two-stage machine learning approach that incorporates market risk regimes and other macro variables to enhance the accuracy of factor timing decisions. The preliminary results of their research show promising improvements in factor timing compared to traditional approaches. The article presents a two-stage machine learning framework for factor timing in investment strategies, using data from the FRED database and Factset to analyze the performance of six common equity factors. The authors demonstrate the effectiveness of their approach through historical out-of-sample testing and compare it to benchmark strategies. They conclude that their framework offers a robust and alternative solution for factor timing in asset pricing and investment strategies. The document also provides contact information for three individuals at The Vanguard Group, Inc. in Malvern, PA.
- Publication
Journal of Portfolio Management, 2024, Vol 50, Issue 3, p132
- ISSN
0095-4918
- Publication type
Academic Journal
- DOI
10.3905/jpm.2023.50.3.132