Library/LLM as a Risk Manager: LLM Semantic Filtering for Lead-Lag Trading in Prediction Markets
ApplicationsResearch Paper

LLM as a Risk Manager: LLM Semantic Filtering for Lead-Lag Trading in Prediction Markets

Sumin Kim, Minjae Kim, Jihoon Kwon, Yoon Kim, Nicole Kagan, Joo Won Lee, Oscar Levy, Alejandro Lopez-Lira, Yongjae Lee, Chanyeol Choi·February 4, 2026·Academic Paper
llms catch spurious correlations that backtests miss, halving average losses in prediction markets

Why It's Worth Reading

Proposes a two-stage screener that uses Granger causality to find lead-lag pairs across Kalshi Economics markets, then passes candidates through an LLM that checks whether the proposed direction has a plausible economic transmission mechanism based on event descriptions. The LLM re-ranker barely moves the win rate (51.4% to 54.5%), but it dramatically shrinks the downside — average losing trade drops from $649 to $347 by filtering out statistically fragile links that look good in backtests but break in practice.

Some technical background helpful

Concepts

Platforms mentioned: Kalshi

Related Reading