Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
Tan, Roberts and Zohren (2023) study momentum and trend following in equities using a feedforward neural network. The abstract mentions transaction costs but not a benchmark, an out-of-sample test, multiple testing or the size of the universe.
“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.”
AssetEquitiesfutures, indices
StrategyMomentum
TechniqueFeedforward network
GeographyUS
Also stated: costs
Missing from abstract: benchmark, out-of-sample test, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodMomentum and trend following by year
FamilyMomentum and trend following289Factor investing240Machine learning return prediction153News sentiment and text signals14818 more · 854
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Extracting Alpha from Financial Analyst Networks by Gorduza et al. | 2024 | ||||
| The Application of Dual-Denoised Momentum Factors in Portfolio Management: A Study of ChiNext Stocks for Retail Investors by Yi | 2025 | ||||
| NoxTrader: LSTM-Based Stock Return Momentum Prediction for Quantitative Trading by Liu et al. | 2023 | ||||
| Machine-Learning the Skill of Mutual Fund Managers by Kaniel et al. | 2021 | ||||
| Dissecting Momentum: We Need to Go Deeper by Borisenko | 2019 |