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

2025-12-02

AI Summary

Prediction markets suffer from semantic fragmentation due to question overlap, implicit equivalence, and logical contradictions, hindering cross-market relational modeling. To address this, we propose the first end-to-end analysis framework powered by autonomous AI agents: leveraging large language models to deeply interpret contract texts and metadata, it integrates semantic clustering with relational reasoning to automatically identify topically coherent market clusters and intra-cluster strong dependencies—including both positive and negative correlations. Our key contributions are twofold: (i) the first application of the autonomous agent paradigm to uncover latent semantic structures in prediction markets, and (ii) the translation of inferred dependencies into actionable, tradeable signals. Evaluated on historical Polymarket data, our framework achieves 60–70% accuracy in dependency prediction, and trading strategies derived from these signals yield an average weekly return of approximately 20%.

Technology Category

• Multiagent Systems: Mechanism Design
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• Clusters prediction markets into coherent topical groups using natural language understanding
• Identifies dependent market pairs with same-outcome or different-outcome relationships
• Translates discovered relationships into trading strategies to quantify actionable signals

Innovation

• Agentic AI pipeline clusters markets using natural language understanding
• Identifies correlated and anti-correlated market pairs via outcome dependencies
• Translates discovered relationships into trading strategies for actionable signals