Reading the Insider Cluster: Concurrent Disclosure-Tone Classification Predicts the Cross-Section of Post-Filing Returns
“The lift is stable across three independent language models (ope- nai gpt-4o-mini, meta-llama Llama-3.3-70b-instruct, deepseek chat-v3.1): the per-vendor lift is +0.50 to +0.52 Sharpe, and the majority-vote, unanimity, and any-POSITIVE aggre- gations fall in a +0.46 to +0.52 Sharpe band.”
StrategyNews sentimentmomentum
TechniqueLarge language modellinear factor model
GeographyUSEurope
Sample window2015–2025
Also stated: Sharpe ratio, Alpha, Long-only, Macro, Text and news, benchmark, costs
Missing from abstract: out-of-sample test, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodNews sentiment and text signals by year
FamilyNews sentiment and text signals148Momentum and trend following289Factor investing240Machine learning return prediction15318 more · 854
AssetEquities97
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Reading the Late-Filing Notification: Form NT Body Narratives Predict Subsequent SEC Restatement Disclosures by Ahn | 2026 | ||||
| Execution-Aware Alpha Mining: Teaching LLM Factor Agents to Account for Trading Costs by Nagireddy | 2026 | ||||
| The Implied-Realized Volatility Ratio and the Cross-Section of Put-Writing Returns by Ahn | 2026 | ||||
| Memorisation or Alpha? Detecting Look-Ahead Contamination in Cross-Sectional Equity Signals by Nguyen | 2026 | ||||
| Beta Recall, Alpha Recall, and a Contamination Detector that Needs No Labels * Measuring Training-data Leakage in LLM Equity Signals by Nguyen | 2026 |