Enhancing Time-Series Momentum Strategies Using Deep Neural Networks

Although time-series momentum is a well-studied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. In this article, the authors introduce deep momentum networks—a hybrid approach that injects deep learning–based trading rules into the volatility scaling framework of time-series momentum. The model also simultaneously learns both trend estimation and position sizing in a data-driven manner, with networks directly trained by optimizing the Sharpe ratio of the signal. Backtesting on a portfolio of 88 continuous futures contracts, the authors demonstrate that the Sharpe-optimized long short-term memory improved traditional methods by more than two times in the absence of transactions costs and continued outperforming when considering transaction costs up to 2–3 bps. To account for more illiquid assets, the authors also propose a turnover regularization term that trains the network to factor in costs at run-time. TOPICS:Statistical methods, simulations, big data/machine learning Key Findings • While time-series momentum strategies have been extensively studied in finance, common strategies require the explicit specification of a trend estimator and position sizing rule. • In this article, the authors introduce deep momentum networks —a hybrid approach that injects deep learning–based trading rules into the volatility scaling framework of timeseries momentum. • Backtesting on a portfolio of continuous futures contracts, Deep Momentum Networks were shown to outperform traditional methods for transaction costs of up to 2–3 bps, with a turnover regularisation term proposed for more illiquid assets.