Quantex Research · Ongoing research · Publications · Note 16 · Research collaboration · Contact

Data and code: Do round numbers predict price reversals in gold?

Replication files for the working paper by Huyen X. Vu (Quantex Research, AlgoTrade Pte. Ltd.), version 3, 24 October 2026. Non-technical summary: Quantex Research note 16.

Data

Hugging Face dataset ZombitX64/xauusd-gold-price-historical-data-2004-2025, file XAU_1d_data.jsonl, revision ff6469dc. SHA-256: cb4cbd244c0ac3245545ecdc33d5364657ab812df4e32dbecb7ea028033a3a19.

Run

python3 -I round_numbers_gold.py XAU_1d_data.jsonl out (Python 3, standard library only, random seed 20261024). It writes all tables below.

Files

• round_numbers_gold.py – analysis script
• tests.csv – holding rates, placebo rates, ranks, rank p, Holm p, descriptive binomial p
• grid_rates.csv – holding rate of every grid, every sample and horizon: written by the script (primary family also printed in the paper appendix)
• boot.csv – month and quarter block bootstrap of the round-minus-placebo difference
• lookback.csv – 1, 5 and 10-day first-touch windows
• flow.csv – sample flow

Licence: free to use with citation of the working paper.

Join us · Research collaboration · Contact · Disclaimer · Risk Disclosure · Privacy Policy