More Strategies, Same Zero: Multiple Testing Against LLM-Scale Alpha Search
“We report two cautionary negatives in the same spirit: two analytic effective-trials shortcuts (a genomics participation-ratio import; an envelope-inversion) both fail, leaving the block bootstrap as the necessary arbiter.”
AssetCrypto
StrategyNews sentimentcarry trade
TechniqueLarge language modelmathematical derivation
Sample window2016–2024
Also stated: Sharpe ratio, Alpha, Text and news, out-of-sample test, costs, multiple testing
Missing from abstract: benchmark, 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
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 | |
|---|---|---|---|---|---|
| From Hypotheses to Portfolios: NeuraQuant for Auditable Crypto-Alpha Discovery with Large Language Model by Zheng and Wang | 2026 | ||||
| Large Language Models and Generative Factor Discovery in Crypto Markets by Sun et al. | 2026 | ||||
| EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading by Mao et al. | 2026 | ||||
| MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models by Kvasiuk et al. | 2026 | ||||
| QuantHarness: Price-Driven Multi-Agent LLMs for High-Frequency Trading by Xiong et al. | 2026 |