Director and Professor of Machine Learning - Oxford-Man Institute of Quantitative Finance, University of Oxford
Co-Founder - Mind Foundry
Conference Day One: 16 September 2019
Monday, September 16th, 2019
While 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 paper, we introduce Deep Momentum Networks -- a hybrid approach which injects deep learning based trading rules into the volatility scaling framework of time series momentum. The model simultaneously learns both trend and position sizing in a data-driven manner, with networks directly trained by optimising the Sharpe ratio of the signal. Backtesting on a portfolio of 88 continuous futures contracts, we demonstrate that the Sharpe-optimised recurrent neural network improved traditional methods by more than two times in the absence of transactions costs, and continued outperforming even when considering transaction costs up to 2-3 basis points. To account for more illiquid assets, we also propose a turnover regularisation term which trains the network to factor in costs at run-time.