Quantitative ResearcharXiv q-finSIGNAL 578FA3

What Survives Honest Evaluation? Leakage-Safe, Search-Aware Assessment of LLM-Driven Trading Strategy Discovery

ORIGINAL / What survives honest evaluation? Leakage-safe, search-aware assessment of LLM-driven trading strategy discovery

A new framework structurally corrects common methodological flaws in LLM-driven trading strategy research, namely look-ahead bias and unaccounted search intensity. By excluding look-ahead via registry-validated tools and recording all evaluations to deflate performance, it provides a more realistic assessment of LLM-discovered strategies and quantifies evidence thresholds for passive benchmarks and human rules.

01 ABSTRACT

The paper presents a strategy-discovery system that structurally avoids look-ahead bias and logs all search attempts. Empirical results show that no LLM-discovered strategy survives honest evaluation, while passive benchmarks pass. The authors argue that pre-registered hypotheses require lower evidence bars than brute-force search and emphasize the large sample sizes needed for credible certification.

02 KEY FINDINGS

  1. Registry-validated tools structurally eliminate look-ahead, and statistical corrections are insufficient without them.
  2. All strategy evaluations are logged and used to deflate reported performance, highlighting the impact of search intensity.
  3. On two datasets (453 US stocks and 39 ETFs), honest evaluation rejected all LLM-discovered strategies and certified passive benchmarks.
  4. A leaky oracle with Sharpe 35 survives Deflated Sharpe and PBO tests, showing the need for structural guards.
  5. Quantifies the large sample sizes required for credible certification of moderate effects and compares human trading rules.
Return to the primary source

AI GENERATED SUMMARY / DISCOVERED BY ARXIV Q-FIN

Read original