polymarket-bot
Unverified ML strategy on Multi by skharchikov. BotFinder score 18 out of 100.
Autonomous prediction-market trading bot: ML ensemble + LLM signals, real-time WebSocket alerts
Source: github
BotFinder analysis pending.
polymarket-bot
Polymarket Signal Bot Research project only. This bot is built for learning and experimentation. It is not intended for production use, and you should not risk real money with it. Use at your own risk. A Cargo workspace containing two independent Rust trading bots for Polymarket prediction markets, backed by a shared library, a Python ML ensemble, and PostgreSQL. - trading-bot — ML-driven signals (XGBoost ensemble + LLM consensus + Bayesian updating) - copy-trading-bot — mirrors trades from top leaderboard traders Both bots run independently with their own Telegram interfaces, and share the same database and common library. Architecture Crate Structure How It Works Trading Bot — ML Pipeline 1. Market fetch — fetches eligible markets from Gamma API (volume, expiry, price filters) 2. Feature engineering — computes 29 features per market (v5): price momentum, volatility, RSI, order book stats, temporal features, 16 NLP features from question text 3. XGBoost ensemble — scores markets via local pure-Rust XGBoost or Python sidecar (XGBoost + LightGBM + HistGBM + ExtraTrees + RF + meta-lear
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)