The Correlation Structure of Anomaly Strategies
90 Pages Posted: 19 Jul 2017 Last revised: 12 May 2020
Date Written: May 12, 2020
We use cluster analysis to consolidate a large number of mean-significant anomalies into cluster portfolios. More than a third of cluster portfolios remain significant under the Hou, Mo, Xue and Zhang (2020) five-factor model – the best performing among six benchmark models considered. A best-first search yields nine factors that subsume all cluster portfolios as well as all significant anomalies, demonstrating the feasibility of a parsimonious description of average realised returns. The search-generated model produces a maximum squared Sharpe ratio of 0.51, a considerable increase in pricing ability relative to current benchmark models.
Keywords: anomalies; correlation; cluster analysis; machine learning; asset pricing
JEL Classification: G12; C38
Suggested Citation: Suggested Citation