Semantic Trading: Agentic AI for Clustering and Relationship Discovery in Prediction Markets
This addresses inefficiencies for prediction market traders by providing a method to discover latent semantic structure, though it appears incremental as it applies existing AI techniques to a specific domain.
The paper tackles the problem of fragmentation in prediction markets by developing an agentic AI pipeline that clusters markets and identifies outcome relationships, achieving 60-70% accuracy in predictions and 20% average returns from derived trading strategies.
Prediction markets allow users to trade on outcomes of real-world events, but are prone to fragmentation through overlapping questions, implicit equivalences, and hidden contradictions across markets. We present an agentic AI pipeline that autonomously (i) clusters markets into coherent topical groups using natural-language understanding over contract text and metadata, and (ii) identifies within-cluster market pairs whose resolved outcomes exhibit strong dependence, including same-outcome (correlated) and different-outcome (anti-correlated) relationships. Using a historical dataset of resolved markets on Polymarket, we evaluate the accuracy of the agent's relational predictions. We then translate discovered relationships into a simple trading strategy to quantify how these relationships map to actionable signals. Results show that agent-identified relationships achieve roughly 60-70% accuracy, and their induced trading strategies earn about 20% average returns over week-long horizons, highlighting the ability of agentic AI and large language models to uncover latent semantic structure in prediction markets.