Mispricing Scanner
A Bayesian dual-agent engine scans prediction markets daily for mispricings. Agent A finds the same event on the other platform (LLM-validated) and compares the price. Agent B is Claude NLP estimating probability from the question. When both diverge from the market by 5pp+, the contract is flagged with Kelly sizing.
Runs daily at 6 AM ET. Results stored and served from Supabase. How it works →
If you're asking whether Kalshi/Polymarket mispricing flags actually pay out: the scanner flags markets where its Bayesian dual-agent engine diverges from the platform price by 5pp or more. HIGH CONFIDENCE means 8pp+ and both agents — cross-platform price match plus Claude NLP — pull the same direction. Roughly 1 in 4daily flags clears HIGH; the rest are MEDIUM or LOW. The Kelly fraction shown is quarter-Kelly by default, sized to the engine's calibrated uncertainty, not the headline edge.
Caveat: a flag is a signal to investigate, not a guaranteed trade. The engine now validates cross-platform matches with an LLM same-event gate, so the old “same name, different event” pairs are filtered out — but still read both contract pages and confirm the resolution criteria before sizing.
What Is the Mispricing Scanner?
The Mispricing Scanner is a daily automated tool that uses a Bayesian dual-agent engine to find prediction markets where the listed price is significantly wrong. It scans both Kalshi (the only CFTC-regulated prediction market in the US) and Polymarket. When both agents independently flag a market as mispriced by 5 percentage points or more, it surfaces with a Kelly-sized position recommendation.
Kalshi is the primary scan — because it's where US traders can actually act on these signals. Polymarket provides the broadest global liquidity. The scanner exploits gaps on both platforms.
How It Works
For each platform: Agent A looks for the same event on the other platform — a title pre-filter, then an LLM gate confirming both contracts resolve on identical criteria before the prices are compared (no validated twin → no cross-reference). Agent B asks Claude for an independent probability estimate. Both feed into a Bayesian weighted average. Divergences of 5pp+ are flagged; 8pp+ at HIGH CONFIDENCE means both agents pull in the same direction.
When to Use This Tool
Check the scanner every morning after 6 AM ET when the daily scan has run. HIGH CONFIDENCE flags are the priority — verify the cross-platform match is the same event, check for overnight news that could explain the gap, then size with the quarter-Kelly fraction shown. This is a signal to investigate, not a guaranteed trade.
MARKET INTELLIGENCE
Find markets where the crowd got it wrong
What is this?
The crowd is often right. But not always. This scanner identifies prediction market contracts where the price seems significantly out of line with real-world data — news, historical base rates, or statistical models.
Think of it as a lie detector for market prices. When a market is way overpriced or underpriced relative to reality, this flags it. You still have to decide — but this gives you the shortlist of where to look.
Real-World Example
→ The Flag
Historical data shows government shutdowns resolve within 14 days 84% of the time. A market asks "Shutdown lasts more than 21 days" — priced at 55¢ (the crowd thinks 55% likely). That's a mispricing signal.
The scanner flags the gap: historical base rate says this should be worth about 16¢, not 55¢. You buy NO at 45¢ (inverse of YES at 55¢) and wait.
✅Action: Use this as your daily deal-finder. Look for anything flagged more than 15 points from the estimated fair value.
Bottom line: The crowd panics, overreacts, and misprices markets every day. This helps you catch it.
Full guide →Related Tools
Frequently Asked Questions
Is the Mispricing Scanner free to use?
The Mispricing Scanner is a Pro tool at $14.99 per month, though it surfaces as a free preview during promotional windows. The daily scan runs at 6 AM ET and stores results in Supabase, so every Pro trader sees the same flagged contracts with Kelly sizing. The free tools — EV Calculator, Probability Converter, and Combo Builder — cover the core math if you want to vet a single contract before subscribing.
How many mispricing flags clear HIGH CONFIDENCE each day?
Roughly 1 in 4 daily flags clears HIGH CONFIDENCE, which requires 8pp or more divergence with both agents agreeing; the rest land at MEDIUM or LOW. That ratio is deliberate — the engine keeps HIGH a genuinely rare, high-conviction tier rather than a label it hands out freely. A quiet day with few HIGH flags usually means the markets are efficiently priced, not that the scanner is broken.
What is the difference between the Kalshi scan and the Polymarket scan?
Both scans flag divergences of 5 percentage points or more using the same Bayesian dual-agent engine, swapping only which platform anchors the price check. On the Kalshi scan, Agent A uses Polymarket as the anchor; on the Polymarket scan, Agent A uses Kalshi. Agent B always asks Claude for an independent estimate. Kalshi is the primary scan because it is the only CFTC-regulated venue where US traders can act on the signal.