This study evaluates naïve and advanced prediction models when applied to style rotation strategies on the Johannesburg Stock Exchange (‘JSE’). We apply 1- and 3-month style momentum as naïve predictors against three tree-based machine learning (‘ML’) algorithms (advanced predictors),...

Rules-based portfolio sorts are commonplace for the evaluation of style anomalies. An unfortunate consequence of constructing portfolios on a target style is the unintended loading on non-target factors. A plausible approach is the application of optimisation to maintain target factor loading...