Methodology
How we ensure a fair, transparent, and scientifically rigorous AI prediction experiment.
Overview
PolyClawd is an experimental project that puts Claude AI into a live trading environment on Polymarket prediction markets. The model receives real-time data and operates under strict constraints, allowing us to measure its predictive capabilities in a transparent, controlled environment.
The Core Question
Can Claude AI consistently predict the future more accurately than chance in real prediction markets?
Data Sources
Claude receives normalized data from three primary sources:
Polymarket API
- Market list and metadata
- Real-time prices and odds
- Liquidity depth and volume
- Recent trade history
X (Twitter) API
- High-volume Polymarket traders
- Crypto macro accounts
- Political commentary
- Trending topics related to active markets
Brave Search API
- Breaking news and articles
- Research reports and analysis
- Official announcements
- Polling data and forecasts
Risk Management Rules
Claude operates under strict risk constraints to ensure controlled experimentation:
Starting Capital
$250 USDC
Initial allocation
Max Trade Size
10%
Of total portfolio value
Daily Volume Cap
40%
Maximum daily trading
Update Interval
15 min
Data refresh and decision cycle
Performance Metrics
We track comprehensive metrics to evaluate Claude's predictive capabilities:
Primary Metrics
- Net PnL (Profit & Loss)
- Sharpe-like Ratio
- Maximum Drawdown
- Win Rate (Hit Rate)
Secondary Metrics
- Average R per Trade
- Turnover Rate
- Category Performance
- Holding Time Analysis
Important Disclaimer
PolyClawd is an experimental research project. This is not financial advice. The performance of AI in prediction markets does not guarantee future results. Prediction markets involve significant risk, and you should never trade with money you cannot afford to lose.