Machine Learning-Driven Long/Short Pair Trading Strategies in Cryptocurrencies
Pairs trading and statistical arbitrage in crypto, studied by Gabriel, Atati and Amara in 2026 with a recurrent neural network. The abstract mentions a Sharpe ratio, profits, drawdowns and a benchmark but not an out-of-sample test, transaction costs, multiple testing or the size of the universe.
“The project first filtered potential pairs with cointegration, then forecasted with LSTM, then used ensemble models for risk-adjusted allocation.”
AssetCryptospot crypto
StrategyPairs tradingmomentum
TechniqueRecurrent neural network
FrequencyDaily
Also stated: Sharpe ratio, Profit, Drawdown, Long-short, Long-only, benchmark
Missing from abstract: out-of-sample test, costs, 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 neighbourhoodPairs trading and statistical arbitrage by year
FamilyPairs trading and statistical arbitrage93Momentum and trend following289Factor investing240Machine learning return prediction15318 more · 909
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 | |
|---|---|---|---|---|---|
| GARCH-LSTM Long/Short Pair Trading Strategies on ETH/BTC pair by Ogwuche et al. | 2026 | ||||
| Research on LSTM-A2C Intelligent Futures Pairs Trading Model Integrating Price Spread Features by Sun et al. | 2026 | ||||
| Pairs trading in cryptocurrency market: A long-short story by Saji | 2025 | ||||
| Cointegrated Portfolios and Volatility modeling in the Cryptocurrency Market by Gabriel and Kunst | 2024 | ||||
| Copula-Based Trading of Cointegrated Cryptocurrency Pairs by Tadi and Witzany | 2023 |