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

arXiv: https://arxiv.org/abs/2302.10175 · HTML: https://mlsanity.com/paper/2302.10175/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Multi-task Sequence to Sequence Learning](https://mlsanity.com/paper/1511.06114/) (2015)
- [Autoregressive Convolutional Neural Networks for Asynchronous Time Series](https://mlsanity.com/paper/1703.04122/) (2017)
- [Enhancing Time Series Momentum Strategies Using Deep Neural Networks](https://mlsanity.com/paper/1904.04912/) (2019)
- [Semi-supervised Multitask Learning for Sequence Labeling](https://mlsanity.com/paper/1704.07156/) (2017)
- [Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture](https://mlsanity.com/paper/2112.08534/) (2021)
- [Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection](https://mlsanity.com/paper/2105.13727/) (2021)
- [Building Cross-Sectional Systematic Strategies By Learning to Rank](https://mlsanity.com/paper/2012.07149/) (2020)
- [Enhancing Cross-Sectional Currency Strategies by Context-Aware Learning to Rank with Self-Attention](https://mlsanity.com/paper/2105.10019/) (2021)

## Built on by (most cited first, 6 of 6)

- [Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies](https://mlsanity.com/paper/2310.10500/) (2023)
- [Deep Learning for Options Trading: An End-To-End Approach](https://mlsanity.com/paper/2407.21791/) (2024)
- [Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models](https://mlsanity.com/paper/2305.06704/) (2023)
- [Network Momentum across Asset Classes](https://mlsanity.com/paper/2308.11294/) (2023)
- [Learning to Learn Financial Networks for Optimising Momentum Strategies](https://mlsanity.com/paper/2308.12212/) (2023)
- [Taming the Greeks: Option Portfolios with Inductive Biases](https://mlsanity.com/paper/2609.33767/) (2026)

## Abstract (arXiv)

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.