Skip to main content
A market priced at 30¢ is saying Yes happens about 30% of the time. Calibration checks that against settled markets: of every market priced in a band some days before it closed, how many resolved Yes?
Each 10-cent band returns markets, avg_price_usd and yes_rate. The gap between them is the band’s edge:
  • yes_rate above avg_price_usd — Yes resolved more often than priced; Yes was cheap.
  • yes_rate below avg_price_usd — Yes was rich, so No was cheap.

​
Where the prices come from

Kalshi history covers tens of thousands of settled markets; Polymarket’s is still small, so many of its bands have too few markets to mean much. Always read markets before reading yes_rate, and remember this is history, not a forecast.
To turn a band into a rule you can act on, with a confidence range and the markets that fit it today, see Strategies.