Visibility Status

This page tracks the current public launch surface for ml-quant-trading.

Live Entry Points

• Repository: https://github.com/initial-d/ml-quant-trading
• Paper: https://arxiv.org/abs/2507.07107
• Hugging Face paper page (verified authorship claim): https://huggingface.co/papers/2507.07107
• Hugging Face synthetic dataset: https://huggingface.co/datasets/dddyym/ml-quant-trading-synthetic
• Hugging Face synthetic MLP checkpoint: https://huggingface.co/dddyym/ml-quant-trading-synthetic-mlp
• alphaXiv page: https://www.alphaxiv.org/abs/2507.07107
• Awesome Quant listing (Factor Analysis): https://github.com/wilsonfreitas/awesome-quant#factor-analysis
• ernie55ernie Awesome Quant listing (Research Frameworks): https://github.com/ernie55ernie/awesome-quant
• Awesome AI Trading Research listing (B1 Factor Investing): https://github.com/ohselab/awesome-ai-trading-research/blob/main/papers.md#b1-factor-investing-23
• v0.1.0 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.1.0
• v0.2.0 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.0
• v0.2.1 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.1
• v0.2.2 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.2
• v0.2.3 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.3
• v0.2.4 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.4
• v0.2.5 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.5
• v0.2.6 release: https://github.com/initial-d/ml-quant-trading/releases/tag/v0.2.6
• PyPI distribution: https://pypi.org/project/mlquantx/
• Six-invariant technical audit: https://github.com/initial-d/ml-quant-trading/blob/main/docs/article_en_six_pipeline_invariants.md
• Six-invariant technical audit (Chinese): https://github.com/initial-d/ml-quant-trading/blob/main/docs/article_zh_six_pipeline_invariants.md
• Technical audit discussion: https://github.com/initial-d/ml-quant-trading/discussions/57
• Zhihu technical article: https://zhuanlan.zhihu.com/p/2069781162151753696
• Cost-metric technical story: https://github.com/initial-d/ml-quant-trading/blob/main/docs/backtest_cost_drag_story.md
• v0.2.4 metric-clarity discussion: https://github.com/initial-d/ml-quant-trading/discussions/49
• Validation dashboard: https://github.com/initial-d/ml-quant-trading/blob/main/docs/validation_dashboard.md
• Zero-account Colab quickstart: https://colab.research.google.com/github/initial-d/ml-quant-trading/blob/main/notebooks/quickstart_colab.ipynb
• Colab Baostock demo: https://colab.research.google.com/github/initial-d/ml-quant-trading/blob/main/demo_baostock.ipynb
• Validation digest: https://github.com/initial-d/ml-quant-trading/blob/main/docs/validation_digest_20260720.md
• Follow-up validation digest: https://github.com/initial-d/ml-quant-trading/blob/main/docs/validation_digest_20260727.md
• Benchmark and reproduction discussion: https://github.com/initial-d/ml-quant-trading/discussions/13
• Benchmark call issue: https://github.com/initial-d/ml-quant-trading/issues/7
• Pairing and public-data validation issue: https://github.com/initial-d/ml-quant-trading/issues/22
• GitHub Community post: https://github.com/orgs/community/discussions/201001
• v0.2.0 community benchmark milestone: https://github.com/initial-d/ml-quant-trading/milestone/1
• Dev Container setup: .devcontainer/devcontainer.json

Completed Contributor Milestones

• First real-machine tensor benchmark report: https://github.com/initial-d/ml-quant-trading/issues/15
• Public-data mini reproduction note: https://github.com/initial-d/ml-quant-trading/issues/14
• First-run onboarding feedback: https://github.com/initial-d/ml-quant-trading/issues/10
• Public-data mini reproduction doc: https://github.com/initial-d/ml-quant-trading/blob/main/docs/public_data_mini_reproduction.md
• Public validation digest for v0.2.0: https://github.com/initial-d/ml-quant-trading/blob/main/docs/validation_digest_20260720.md
• Public validation digest for v0.2.1: https://github.com/initial-d/ml-quant-trading/blob/main/docs/validation_digest_20260727.md
• External cost-metric review and compatibility fix: https://github.com/initial-d/ml-quant-trading/pull/47

Current Contributor Funnel

• Community CPU/GPU benchmarks: https://github.com/initial-d/ml-quant-trading/issues/7
• Paired public-data validation and benchmark work: https://github.com/initial-d/ml-quant-trading/issues/22
• Benchmark and reproduction reports: https://github.com/initial-d/ml-quant-trading/discussions/13

Traffic Snapshot

Recorded on 2026-08-12 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-08-10):

• Views: 1,175 total, 301 unique visitors.
• Clones: 755 total, 323 unique cloners.
• Repository stars/forks/watchers at snapshot time: 69 stars, 30 forks, 4 watchers.
• Top external referrers by visits: Google (99), arXiv (63), ChatGPT (23), JoinQuant (20), Zhihu (17), Doubao (16), Bing (7), the project site (5), and Hugging Face (4). These are visits, not unique-user totals.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, docs/validation_dashboard.md, discussion #43, issue #22, and Releases.

Operating takeaways:

• The August 9 technical-content pulse produced the window's highest unique visitor day (65), while August 10 retained 128 total views. This is a useful signal for continuing evidence-led technical publishing rather than generic promotional posts.
• Search, arXiv, Chinese community links, and AI assistants are all delivering attributable discovery; no single external source dominates acquisition.
• The next conversion target is an independent technical-audit, benchmark, or public-data report. A dedicated technical-audit issue form now lowers the reporting cost for both successful and failed runs.

Recorded on 2026-08-10 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-08-08):

• Views: 1,072 total, 245 unique visitors.
• Clones: 884 total, 369 unique cloners.
• Repository stars/forks/watchers at snapshot time: 68 stars, 30 forks, 4 watchers.
• PyPI mlquantx downloads: 112 in the latest day and 195 in the latest week; these counts include automated clients and are not unique-user totals.
• Hugging Face downloads: 52 for the synthetic dataset and 10 for the MLP model.

The post-release usage signals are growing faster than stars. Track the next snapshot for sustained installs, GitHub referrals, and community reports rather than interpreting raw download or clone counts as unique adoption.

Recorded on 2026-08-05 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-08-03):

• Views: 1,189 total, 236 unique visitors.
• Clones: 774 total, 349 unique cloners.
• Repository stars/forks/watchers at snapshot time: 66 stars, 29 forks, 4 watchers.
• Top referrers: GitHub, Google, Bing, Zhihu, JoinQuant, Doubao, ChatGPT, arXiv, the project site, and Baidu.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, the main tree view, releases, issue #22, issue #7, and contributor PRs.

Operating takeaways:

• Unique cloners continue to rise even while views normalize after the launch spike, which suggests deeper evaluation by a smaller but more committed audience.
• Chinese-language surfaces remain the strongest non-root discovery path.
• The August reproduction challenge needs repeated light-touch reminders because issue #7 and issue #22 are still visible in traffic but not yet converting into many new public reports.
• A second August 5 outreach pulse targeted high-relevance A-share, factor, public-evidence, walk-forward, and live-trading safety threads; monitor these for maintainer replies before posting any follow-up.

Recorded on 2026-08-03 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-08-01):

• Views: 1,332 total, 265 unique visitors.
• Clones: 745 total, 335 unique cloners.
• Repository stars/forks/watchers at snapshot time: 66 stars, 29 forks, 4 watchers.
• Top referrers: GitHub, Google, Bing, Zhihu, JoinQuant, Doubao, ChatGPT, arXiv, Baidu, and DuckDuckGo.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, the main tree view, issue #22, and contributor benchmark/reproduction issues.

Operating takeaways:

• Star growth continued through the weekend while unique cloners also increased, suggesting the new reproduction challenge is being tried rather than only viewed.
• Chinese discovery is now more visible: Zhihu and JoinQuant both appear as referrers, and README.zh-CN.md remains the top non-root path.
• The second awesome-list entry broadens the durable external discovery surface beyond launch-time social posts.

Recorded on 2026-07-31 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-07-29):

• Views: 1,374 total, 251 unique visitors.
• Clones: 658 total, 314 unique cloners.
• Repository stars/forks/watchers at snapshot time: 60 stars, 29 forks, 4 watchers.
• Top referrers: GitHub, Google, Bing, arXiv, Doubao, Zhihu, Baidu, ChatGPT, DuckDuckGo, and the project site.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, issue #22, discussion #13, and contributor PRs.

Operating takeaways:

• The project is still growing after the initial launch spike: stars and forks both increased while clone traffic stayed strong.
• Chinese-language onboarding remains a meaningful entry point, now supported by a dedicated Chinese validation article and community post drafts.
• Search and paper surfaces are contributing stable discovery, not only one-off GitHub Community traffic.

Recorded on 2026-07-30 from GitHub's rolling 14-day traffic window (latest daily bucket available through 2026-07-28):

• Views: 1,303 total, 240 unique visitors.
• Clones: 621 total, 307 unique cloners.
• Repository stars/forks/watchers at snapshot time: 57 stars, 28 forks, 4 watchers.
• Top referrers: GitHub, Google, Bing, arXiv, Zhihu, Baidu, ChatGPT, DuckDuckGo, Doubao, and the project site.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, issue #22, discussion #13, and contributor PRs.

Operating takeaways:

• Clone interest remains unusually strong relative to stars, suggesting some visitors are testing or archiving the project rather than only bookmarking it.
• Chinese-language onboarding and the factor handbook remain real discovery surfaces.
• Search, arXiv, and GitHub internal discovery are all contributing traffic.

Recorded on 2026-07-27 from GitHub's rolling 14-day traffic window:

• Views: 1,206 total, 246 unique visitors.
• Clones: 465 total, 249 unique cloners.
• Repository stars/forks at snapshot time: 54 stars, 28 forks.
• Follow-up pulse during outreach on 2026-07-27: 55 stars, 28 forks, 4 watchers.
• Top referrers: GitHub, Google, Bing, arXiv, ChatGPT, Zhihu, Baidu.
• High-interest paths beyond the repository root: README.zh-CN.md, docs/factor_handbook.md, issue #22, discussion #13, and contributor PRs.

Operating takeaways:

• Chinese-language onboarding and the factor handbook are real discovery surfaces.
• arXiv and search traffic are already contributing steady external discovery.
• Contributor-facing issues and discussions are receiving enough traffic to keep benchmark/reproduction asks visible.

Artifact Boundary

• Public artifacts should be synthetic, metadata-only, or generated from clearly redistributable data.
• Do not publish proprietary, paid, or license-unclear market data as repository or Hugging Face artifacts.
• Hugging Face is useful as a paper and demo-artifact entry point, not as a place to mirror restricted financial datasets.

Current Positioning

Short description:

PyTorch research stack for ML multi-factor trading: 213 factors, bias correction, portfolio optimization, and vectorized backtesting.

Primary ask:

Share CPU/GPU benchmark results, public-data reproduction notes, and setup feedback.

Operating Rules

• Do not buy stars, forks, followers, comments, or fake traffic.
• Do not mass-post identical messages across communities.
• Post only where quantitative finance, PyTorch, reproducibility, or research software is on-topic.
• Prefer asking for benchmark/reproduction feedback over asking for stars.
• Link back to the discussion thread for open-ended reports and to issues for reproducible bugs.

Next Iterations

• Add more real benchmark results to docs/benchmark_board.md.
• Add more public-data mini reproductions with larger or differently constructed universes.
• Ask new users to try the Dev Container and report first-run friction.
• Post the v0.2.1 validation entrypoint release to one relevant community at a time with a customized note.
• Invite reproducibility feedback through the live synthetic Hugging Face dataset and model cards.
• Follow up on open high-relevance awesome-list pull requests after maintainers have had time to review.
• Follow up on the auto-refreshed Awesome Quant listing PR after maintainer review.
• Set a GitHub social preview image through repository settings when browser upload access is available.
• Convert useful discussion replies into docs, issues, or benchmark board entries.