Understand the project
Practical overview
When it fits
Use it to explore or compare the included approaches in backtests with price data you supply, not to infer proven live-trading profitability.
Who it is for
- People studying pairs-trading methods and backtesting.
- Python users who want to explore the project’s distance, rolling OLS, Kalman-filter and proposed reinforcement-learning approaches.
Documented uses
- Compare distance-based and cointegration-based pairs-trading approaches.
- Explore a proposed reinforcement-learning agent for pairs trading.
- Backtest strategies using price data.
Before you choose
Requirements & limits
The public repository is licensed under MIT. The project is no longer being developed.
- Dependencies are installed using the README’s ./setup.sh instruction.
- The authors’ Interactive Brokers data is not included; users can use their own price data.
- Reported returns are from backtesting, and the README warns about possible lookahead bias and unproven live profitability.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Source-based practical guide
Set up the project dependencies
Install the project dependencies using the setup step specified in the README.
Before you start
- Access to the public GitHub repository.
Steps
Obtain the repository.
Run ./setup.sh from the project.
Expected outcome
The README’s documented dependency-installation step has been run.
Guide limitations
- The README does not specify a subsequent command for running experiments.
- The financial data used by the authors is not included; experiments require price data of your own.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- wywongbd/pairstrade-fyp-2019 · Official homepage title · retained in its source language