微软牛逼框架 ✅ 自动挖掘Alpha因子 - 自动构思成千上万个因子公式，写代码验证，优胜劣汰 ✅ 自动优化预测模型 - 不仅调参，还能修改模型结构，尝试不同神经网络架构 ✅ 从研报/财报提取因子 - 阅读PDF，提取有价值数据转化为可用因子 ✅ R&D闭环工作流 - R(Research)负责想，D(Development)负责干，互相配合迭代 ✅ 24小时不知疲倦 - 暴力穷举出意想不到的有效因子 ✅ 自动化搬
Python · active 2025-03-26 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 500 days from 2025-03-26 to 2026-08-07. Pushes: 1,561 total, peak 28 in a day. Pull requests: 483 total, peak 26 in a day. Issues: 69 total, peak 3 in a day. Comments: 551 total, peak 33 in a day. Stars: 3,782 total, peak 101 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| you-n-g | 635 | 304 | 88 | 177 |
| XianBW | 225 | 146 | 65 | 8 |
| Hoder-zyf | 219 | 143 | 38 | 28 |
| peteryang1 | 215 | 135 | 57 | 16 |
| qew21 | 209 | 168 | 35 | 3 |
| Jensen246 | 152 | 138 | 11 | 3 |
| RolandMinrui | 116 | 98 | 17 | 1 |
| SunsetWolf | 105 | 44 | 20 | 39 |
| jingyuanlm | 101 | 94 | 7 | 0 |
| WinstonLiyt | 95 | 59 | 28 | 7 |
| microsoft-github-policy-service[bot] | 74 | 0 | 0 | 74 |
| xuangu-fang | 72 | 57 | 9 | 3 |
| couragec | 53 | 53 | 0 | 0 |
| Copilot | 50 | 5 | 1 | 39 |
| dependabot[bot] | 46 | 2 | 41 | 3 |
| github-advanced-security[bot] | 34 | 0 | 0 | 23 |
| chelsea97 | 23 | 22 | 1 | 0 |
| TPLin22 | 14 | 6 | 4 | 2 |
| inevity | 9 | 0 | 1 | 6 |
| ultmaster | 9 | 9 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#1442tolivetoearn-debug2026-07-21 12:18fix(qlib): isolate holdout evaluation from iterative research feedback
- Pull request#1424dependabot[bot]2026-06-15 18:02
- Pull request#1424dependabot[bot]2026-06-15 18:02
- Pull request#1424dependabot[bot]2026-06-15 18:02
- Issue comment#1420microsoft-github-policy-service[bot]2026-05-24 00:30Feat/terminal phase3 execution
- Issue comment#1410microsoft-github-policy-service[bot]2026-05-12 08:56fix(factor_coder): prevent per-instrument ML training hang in factor code
- Pull request#1403dependabot[bot]2026-04-29 01:43
- Pull request#1403dependabot[bot]2026-04-29 01:43
- Issue comment#1395huqian19842026-04-26 02:12feat(litellm): add support for embedding extra parameters and OpenAI-Compatible Endpoints
- Pull request#1391dependabot[bot]2026-04-15 19:46
- Issue#1387haimfink917-eng2026-04-15 04:41使用测试集回测结果作为sota因子或者模型迭代的依据，是否存在数据泄露或者过拟合问题呢？
- Issue comment#1382SunsetWolf2026-04-13 05:31How to properly train intraday (1-minute) high-frequency factors with fin_quant?
- Issue comment#1382SunsetWolf2026-04-13 04:55How to properly train intraday (1-minute) high-frequency factors with fin_quant?
- Pull request#1385dependabot[bot]2026-04-12 10:37
- Pull request#1385dependabot[bot]2026-04-12 10:37
- Issue#1382Mrwuliang2026-04-11 12:15How to properly train intraday (1-minute) high-frequency factors with fin_quant?
- Pull request#1381dependabot[bot]2026-04-10 03:54
- Pull request#1381dependabot[bot]2026-04-10 03:54
- Issue comment#1334hangpengjie2026-04-04 08:55RD-Agent UI development part code display issue
- Issue comment#1378microsoft-github-policy-service[bot]2026-04-03 04:06Add Railway deployment and Supabase persistence
- Pull request#1378joshuayash2026-04-03 04:05
- Issue comment#1372baolicheng0510-code2026-04-01 05:52"The running time exceeds 3600 seconds" during backtest
- Issue comment#1371iCloudys2026-03-27 01:39SiliconFlow embedding errors (deepseek method)
- Pull request#1369Alex-wuhu2026-03-22 11:01
- Pull request#1365dependabot[bot]2026-03-18 06:28
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3,782 stars here means stars gained during the window, not the repo's star count.