Trading on mean-reversion in energy futures markets

Abstract

We study whether simple technical trading strategies enjoying large popularity among practitioners can be employed profitably in the context of hedge portfolios for Crude Oil, Natural Gas, Gasoline and Heating Oil futures. The strategies tested are based on mean-reverting calendar spread portfolios established with dynamic hedge ratios. Entry and exit signals are generated by so-called Bollinger Bands. The trading system is applied to twenty-two years of historical data from 1992 to 2013 for various specifications, taking transaction costs into account. The significance of the results is evaluated with a bootstrap test in which randomly generated orders are compared to orders placed by the trading system. Whereas we find most combinations involving the front-month and second-month futures to be significantly profitable for all commodities tested, the best results for the risk-adjusted Sharpe Ratio are obtained for WTI Crude Oil and Natural Gas, with Sharpe Ratios in excess of 2 for most combinations and a rather smooth performance for all calendar spreads. Based on our results, there is a serious doubt whether energy futures markets can be considered weakly efficient in the short-term.