Polymarket Trading Agent

Prediction markets price real-world events as tradeable contracts. When the market price diverges from the true probability, there's an edge to exploit. This bot autonomously identifies these mispricings, researches the underlying events, estimates true probabilities, and executes trades — all without human intervention.

The system orchestrates 13 specialized agents — market scanner, 3 researchers (web, news, data), 4 independent estimators (base, contrarian, calibration, Bayesian), an aggregator, risk manager, trader, orchestrator, and portfolio monitor. Each agent has a focused responsibility and communicates through structured interfaces. Every trade flows through a 5-stage pipeline ending in execution via the Polymarket CLOB API with slippage protection.

The system evolved through 4 major versions. V1 used a single LLM estimator and lost money. V2 introduced multi-estimator consensus. V3 added Platt calibration to fix systematic overconfidence. V4 pivoted to weather ensemble trading — using 139 numerical weather model members instead of LLM estimation for weather markets, dramatically improving accuracy on the highest-volume market category.

The weather trading module queries 139 ensemble members across 4 major forecast systems: GFS (30 members), ECMWF (50 members), ICON (39 members), and GEM (20 members). By counting what fraction of ensemble members predict a given outcome, the system generates calibrated probability estimates for temperature, precipitation, and extreme weather markets — without relying on LLM estimation at all.

Every trade must pass 11 independent risk checks before execution — maximum drawdown limits, concentration caps, correlation prevention, daily loss limits, cooldown periods after losses, and position count caps. The quarter-Kelly criterion keeps position sizes conservative, betting only 25% of the theoretically optimal amount.