Call for benchmarks and public-data reproductions

[initial-d]

I am opening this as the first public outreach thread for ml-quant-trading.

The project is an end-to-end PyTorch research stack for ML-enhanced multi-factor trading:

• 213 factor dimensions
• masked tensor factor primitives
• limit-up / limit-down / halt bias correction
• MLP and Transformer baselines
• Markowitz portfolio construction
• vectorized backtesting and metrics
• synthetic and public-data demos
• CI, tests, benchmark scripts, and contribution templates

I would especially appreciate two kinds of feedback:

1. CPU/GPU benchmark reports

   • Run make benchmark or the larger command in docs/benchmarking.md.
   • Submit results with the Benchmark result issue template.

2. Public-data reproductions

   • Try notebooks/public_factor_ic.ipynb.
   • Report whether the workflow runs on your machine.
   • Suggest or contribute a small public-data case study.

Useful links:

• Start here: https://github.com/initial-d/ml-quant-trading/blob/main/docs/start_here.md
• Benchmark board: https://github.com/initial-d/ml-quant-trading/blob/main/docs/benchmark_board.md
• FAQ: https://github.com/initial-d/ml-quant-trading/blob/main/docs/faq.md
• Paper: https://arxiv.org/abs/2507.07107

This is a research and engineering baseline, not financial advice or a live trading system.

[initial-d]

I also added a copy-ready outreach page for sharing this project with relevant communities without spam:

https://github.com/initial-d/ml-quant-trading/blob/main/docs/community_outreach.md

Best current asks:

• CPU/GPU benchmark results
• public-data reproduction reports
• factor-engine edge cases
• documentation/setup feedback

Please customize posts for each community and avoid implying live trading profitability.

[initial-d]

A dedicated discussion thread is now open for benchmark results, public-data reproductions, and setup feedback:

#13

Issues are still welcome for concrete bugs or reproducible failures; the discussion thread is better for reports, comparisons, and exploratory reproduction notes.