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

Paper: arXiv 2302.10175

Authors: Wee Ling Tan, Stephen Roberts, Stefan Zohren

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.

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper provides an original unification of time-series and cross-sectional momentum using spatio-temporal neural networks. Its empirical evaluation is strong, incorporating realistic transaction costs and turnover regularization across equities and futures.

Research Flowchart

  flowchart TD
    A[Research Goal: Unify Time-Series & Cross-Sectional Momentum Strategies] --> B[Data Inputs: 46 US Equities & 12 Equity Index Futures Contracts]
    B --> C[Methodology: Neural Networks with Spatio-Temporal Momentum Features]
    C --> D[Model Training & Optimization: Apply LASSO Shrinkage & Turnover Regularization]
    D --> E[Backtesting: Evaluate Performance under High Transaction Costs 5-10 bps]
    E --> F[Outcomes: Single-Layer Model Outperforms Benchmarks & Retains Gains Despite Transaction Costs]