Semantic Trading: Agentic AI for Clustering and Relationship Discovery in Prediction Markets

TL;DR

This paper introduces an agentic AI system that clusters prediction markets and discovers relationships among them using natural language understanding, leading to improved trading strategies with significant returns.

Contribution

The paper presents a novel AI pipeline that autonomously clusters markets and identifies dependent relationships, enhancing understanding and trading in prediction markets.

Findings

Relational predictions achieved 60-70% accuracy.

Trading strategies based on discovered relationships earned about 20% returns.

Demonstrates the effectiveness of agentic AI in uncovering semantic market structures.

Abstract

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.