2019/04/30 by Bryan Lim, Stefan Zohren, Stephen Roberts · 1 citation
Mathematics · Computer Science · Economics, Econometrics and Finance · #stat.ML #cs.LG #q-fin.TR
published as The Journal of Financial Data Science, Fall 2019
arxiv created 2020/09/27 · arxiv updated 2020/09/29
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 also simultaneously learns both trend estimation 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 LSTM improved traditional methods by more than two times in the absence of transactions costs, and continue outperforming 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.