QuantPits
Unverified ML strategy on Multi by DarkLink. BotFinder score 18 out of 100.
An advanced, production-ready quantitative trading system built on top of Microsoft Qlib
Source: github
BotFinder analysis pending.
QuantPits
QuantPits An advanced, production-ready quantitative trading system built on top of Microsoft Qlib. This system provides a complete end-to-end pipeline for weekly and daily frequency trading, featuring modular architecture, multi-instance isolation (Workspaces), ensemble modeling, execution analytics, and interactive dashboards. 📄 Read our paper: arXiv:2604.11477 ⚔️ Enter QuantPits Arena: Our empirical strategy tournament and benchmark zoo, where prospective multi-model strategies are stress-tested against 28 execution animals and 11,000 parametric random monkeys—with full decision archaeology. 🌐 中文版本 (READMEzh.md) Note: We welcome contributions! If you find a bug or have a feature suggestion, please feel free to open an Issue or submit a Pull Request. 🚀 Key Features Multi-Workspace Isolation: Spin up independent "Pits" for different markets (e.g., CSI300, CSI500) or configurations without duplicating code. Component-Based Pipeline: - Train & Predict: Support for both full and incremental training on multiple models (LSTM, GRU, Transformers, LightGBM, GATs). - Brute Force & Ensemble:
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)