There has been considerable research into dynamic global tactical asset allocation (GTAA) strategies driven by simple measures of Valuation and Momentum applied to a baseline balanced portfolio of equities and fixed income (see Blitz and van Vliet 2008, Wang and Kochard 2011, Gnedenko and Yelnik...

We develop a new method that detects jumps nonparametrically in financial time series and significantly outperforms the current benchmark on simulated data. We use a long short- term memory (LSTM) neural network that is trained on labelled data generated by a process that experiences both jumps...

Despite momentum's strong historical performance, its returns have large negative skewness and occasionally experiences persistent strings of sharp negative returns, referred as "momentum crashes" in the recent literature. I argue that momentum crashes are due to crowded trades which push prices...

We show how one can use deep neural networks with macro-economic data in conjunction with price-volume data in a walk-forward setting to do tactical asset allocation. Low cost publicly traded ETFs corresponding to major asset classes (equities, fixed income, real estate) and geographies (US,...

The description of the dynamics and fluctuations of macro variables remains one of the most exciting problems of financial economics. This paper models macro variables via the description of transactions between agents. We use risk ratings x of agents as their coordinates in the economic space....

We compare several representative sophisticated model averaging and variable selection techniques of forecasting stock returns. When estimated traditionally, our results confirm that the simple combination of individual predictors is superior. However, sophisticated models improve dramatically...