How It Works
Whale / Insider Detection
Scans Polymarket for unusually large trades that may indicate insider knowledge. Focuses on markets where non-public information is plausible — political decisions, regulatory rulings, corporate announcements, legal outcomes.
1. Market Selection
Only markets matching insider-prone keywords are scanned: executive order, president, congress, senate, election, appointment, cabinet, FDA, SEC, FTC, approval, ruling, regulation, CEO, earnings, merger, acquisition, announce, launch, court, verdict, trial, settlement, indictment, bitcoin, ethereum, tariff, sanctions, policy, resign, hire, fire
Additional filters: volume $10K–$500K, price 5¢–95¢ (not resolved), still active.
2. Whale Trade Detection
For each candidate market, recent trades are fetched from the Polymarket API. A trade is flagged as a "whale" if it meets both conditions:
- Trade size > 5x the median trade size for that market
- Trade size > $500 (absolute floor to filter noise)
Whale trades are then clustered by wallet address to identify accumulated positions.
3. Insider Score (0–100)
Each whale address gets a composite score from 5 factors:
| Factor | Max Points | How It's Calculated |
|---|---|---|
| Whale Multiple | 25 | How many times larger than median trade size. 10x = 25 pts. |
| Contrarian | 25 | Betting against market consensus? (e.g., big YES buy when price <25¢) = 25 pts. With consensus = 5 pts. |
| Category | 20 | Political/regulatory = 20, legal = 18, corporate = 15, crypto = 12, other = 5. |
| Concentration | 15 | What % of recent market volume comes from this one address. 20%+ = 15 pts. |
| Timing | 15 | How close to the market's resolution date. Last 20% of market life = 15 pts, last 40% = 10 pts. |
Timing Opportunities
Finds announcement-driven markets closing soon where the answer may be knowable before the market fully prices it in.
Pipeline
- Identify — find markets closing within 48h that are announcement-driven (FDA, court, earnings, policy, etc.)
- Filter — exclude sports, entertainment, weather (outcomes with instant mass awareness)
- Score — off-hours close, urgency, price uncertainty, region relevance, resolution source
- Research — Claude analyzes top 3 candidates to hunt for the answer
- Signal — if AI finds an edge, creates an opportunity with trade direction
The key insight: the outcome often becomes known (via announcement, filing, press release) before the market fully adjusts — especially during off-hours when fewer traders are watching.
AI Research (Information Asymmetry)
Uses Claude to deeply research individual markets and estimate the true probability, looking for cases where the crowd is wrong.
Candidate Selection
- Volume < $100K (less efficient pricing)
- Exploitable categories: entertainment, pop culture, science, tech, crypto, sports
- Mid-range prices: 15¢–85¢ (most exploitable bias zone)
- Early in market life (<25% elapsed = most mispriced period)
Research Process
Claude (Opus) analyzes each candidate by:
- Identifying what data/evidence determines the outcome
- Checking historical base rates and precedents
- Assessing current conditions and recent developments
- Identifying crowd blind spots and biases
- Generating a calibrated probability estimate
An opportunity is created when the weighted edge exceeds 8% (edge = |AI probability − market price|, weighted by confidence: high=1.0, medium=0.6, low=0.3).
Paper Trading
High-confidence opportunities are automatically paper traded to validate strategies.
- Starting bankroll: $1,000 (simulated)
- Max position: 10% of bankroll per trade
- Auto-trade threshold: edge ≥ 5%, confidence ≥ 70%
- Position sizing: quarter-Kelly criterion
- Simulated 2% winner fee (approximation for Polymarket)
- Auto-closes on market resolution or expiry