Memorisation or Alpha? Detecting Look-Ahead Contamination in Cross-Sectional Equity Signals
“Traded as a portfolio that is long and short in equal size, so that it does not bet on the market's direction, the same signal earns an annualised Sharpe ratio, return divided by the volatility of that return, of +2.14 in window and +0.40 out.”
AssetEquitiessingle stocks
StrategyNews sentiment
TechniqueLarge language model
GeographyUS
Also stated: Monthly, Sharpe ratio, Alpha, Long-short, Text and news
Missing from abstract: benchmark, out-of-sample test, costs, 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 | |
|---|---|---|---|---|---|
| Beta Recall, Alpha Recall, and a Contamination Detector that Needs No Labels * Measuring Training-data Leakage in LLM Equity Signals by Nguyen | 2026 | ||||
| Execution-Aware Alpha Mining: Teaching LLM Factor Agents to Account for Trading Costs by Nagireddy | 2026 | ||||
| LLM-Based High-Growth Potential Ranking and Portfolio Selection: Evidence from China's Optical Industry by Lin and Xue | 2026 | ||||
| Trials-adjusted Out-of-Sample Gating for LLM-proposed Trading Strategies by Olagoke | 2026 | ||||
| Generative AI-Based High-Growth Potential Ranking for Portfolio Construction: Evidence from China's Optical Industry by Lin and Xue | 2026 |