We provide evidence that a simple moving average timing strategy, when applied to portfolios of commodity futures, can generate superior performance to the buy-and-hold strategy. The outperformance is very robust. It can survive the transaction costs in the futures markets, it is not...

We examine the ability of idiosyncratic skewness to explain the cross section of commodity futures returns at both the characteristic and factor levels. We find that idiosyncratic skewness negatively and significantly predicts cross-sectional commodity futures returns, and largely accounts for...

This paper uses machine learning tools to study the serial dependence (lead-lag relations) of commodity futures returns during the post financialization period (January 2004 – December 2019). We use LASSO (Least Absolute Shrinkage and Selection Operator) to select the predictors as the number...