When Missing Becomes Structure: Intent-Preserving Policy Completion from Financial KOL Discourse

2026-04-15

AI Summary

This study addresses the challenge of translating unstructured investment opinions expressed by financial key opinion leaders (KOLs) on social media into executable trading strategies that faithfully preserve their original intent, without imposing subjective assumptions about unspecified execution details such as timing, position sizing, or holding periods. It introduces, for the first time, a framework termed “intent-preserving strategy completion,” which treats missing information in KOL utterances as a structural characteristic rather than noise. The approach leverages multimodal discourse understanding to extract directional intent and employs offline reinforcement learning augmented with intent-alignment constraints to automatically complete missing execution decisions. Experiments on YouTube and X platform data from 2022 to 2025 demonstrate that the method achieves zero unsupported trades and zero directional reversals while improving returns by 18.9% over KOL-aligned baselines and attaining the highest Sharpe ratio.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Multimodal Learning

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it into executable trading strategies without injecting assumptions about unspecified execution decisions remains an open problem. We observe that the gaps in KOL statements are not random deficiencies but a structured separation: KOLs express directional intent (what to buy or sell and why) while leaving execution decisions (when, how much, how long) systematically unspecified. Building on this observation, we propose an intent-preserving policy completion framework that treats KOL discourse as a partial trading policy and uses offline reinforcement learning to complete the missing execution decisions around the KOL-expressed intent. Experiments on multimodal KOL discourse from YouTube and X (2022-2025) show that KICL achieves the best return and Sharpe ratio on both platforms while maintaining zero unsupported entries and zero directional reversals, and ablations confirm that the full framework yields an 18.9% return improvement over the KOL-aligned baseline.

Problem

• Key Opinion Leader
• trading strategy
• execution decisions
• intent preservation
• policy completion

Innovation

• intent-preserving policy completion
• offline reinforcement learning
• KOL discourse
• structured missingness
• trading strategy generation