Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies

TL;DR

This paper introduces Spatio-Temporal Momentum strategies using neural networks to jointly learn time-series and cross-sectional momentum features, improving trading performance and robustness against transaction costs.

Contribution

It proposes a neural network framework that unifies time-series and cross-sectional momentum strategies, demonstrating effective trading signals across multiple assets.

Findings

Neural network models effectively generate trading signals for all assets.

The approach maintains performance under high transaction costs.

Regularization enhances model robustness and profitability.

Abstract

We introduce Spatio-Temporal Momentum strategies, a class of models that unify both time-series and cross-sectional momentum strategies by trading assets based on their cross-sectional momentum features over time. While both time-series and cross-sectional momentum strategies are designed to systematically capture momentum risk premia, these strategies are regarded as distinct implementations and do not consider the concurrent relationship and predictability between temporal and cross-sectional momentum features of different assets. We model spatio-temporal momentum with neural networks of varying complexities and demonstrate that a simple neural network with only a single fully connected layer learns to simultaneously generate trading signals for all assets in a portfolio by incorporating both their time-series and cross-sectional momentum features. Backtesting on portfolios of 46 actively-traded US equities and 12 equity index futures contracts, we demonstrate that the model is able to retain its performance over benchmarks in the presence of high transaction costs of up to 5-10 basis points. In particular, we find that the model when coupled with least absolute shrinkage and turnover regularization results in the best performance over various transaction cost scenarios.