Home / Trading bots
rustyneuron01/Polymarket-Sports-Trading-Bot
ML-driven sports prediction and trading bot for Polymarket
What it is
A Python trading bot that predicts sports game outcomes with machine learning models trained on historical data, then trades the corresponding markets on Polymarket. It covers two modes: a pre-game model that estimates win probability and trades when it implies an edge over market prices, and an in-game model that uses score, clock, and price data to signal buy-low and sell-high opportunities. The data-to-train-to-predict-to-trade pipeline currently implements NHL (via ESPN and Polymarket), making it a good fit for developers interested in sports-market modeling who can extend it to other sports. It ships with paper trading by default, and live trading execution is included, though the current implementation is limited to a single sport.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Developers |
|---|---|
| Used for | Live trading, Strategy research |
| Markets | Crypto, Other markets |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | Medium 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): +2 over the period, now 136. Gaps mean no snapshot was taken that day.
Predict game results with ML models trained on historical data; trade on Polymarket Sports(NHL, NBA, Tennis etc). Data → train → predict → trade.
Similar tools
Machine learning signal generation and automated trading in Python
Ensemble-based Python crypto trading bot for Binance
Open source Python crypto trading bot with visual interface
Python crypto trading bot with machine learning optimisation
Student project trading Indian stocks live through Zerodha with AI
Python starter kit for machine learning trading bots on Binance