Home / Factor research
wywongbd/pairstrade-fyp-2019
Comparing distance, cointegration and RL approaches to pair trading
What it is
A research project that tests three approaches to pair trading: the distance method, cointegration and reinforcement learning. Full code and experiment steps are included so the comparison can be reproduced. Quant researchers, students and developers interested in statistical arbitrage and machine learning strategies will find a useful case study. It started as a student project, so the findings reflect its specific data and setup.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Strategy research, Backtesting |
| Markets | US equities, Multi-market |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | Low practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +1 over the period, now 273. Gaps mean no snapshot was taken that day.
We tested 3 approaches for Pair Trading: distance, cointegration and reinforcement learning approach.
Similar tools
Event-driven backtesting engine for Python trading algorithms
Lightweight deep reinforcement learning framework for portfolio management
Python collection of online portfolio selection algorithms
Vectorized pandas backtester and trading engine for QuantRocket
Pythonic event-driven backtesting library for trading algorithms
Machine learning framework for trading systems and market analysis