QuantsPlaybook Turns 100+ Chinese Brokerage PDFs Into Runnable Python Backtests
A Chinese quant repo reproducing 100+ brokerage research strategies is trending, bundling RSRS timing, factor models, and HHT algorithms into runnable notebooks.
- QuantsPlaybook hit 6,254 stars reproducing 100+ Chinese brokerage quant research strategies as runnable notebooks.
- Four tracks: 25+ timing strategies, 22+ factor models, plus value and portfolio optimization examples.
- Includes multiple RSRS variants, HHT models, Trader-Company algorithm, and STR salience factor reproductions.
- Built on Qlib, Backtrader, PyTorch, LightGBM, with data from JQData and Tushare Pro.
- A-share focused with Chinese-language documentation; backtest assumptions inherit typical sell-side research limitations.
- Repo link: github.com/hugo2046/QuantsPlaybook
QuantsPlaybook turns brokerage research into runnable code
QuantsPlaybook, a GitHub repository that reproduces quantitative research from Chinese brokerages, has passed 6,000 stars. Its Jupyter notebooks implement strategies for China’s A-share market, covering data ingestion, signal construction, backtesting and visualization.
Most sell-side reports describe a signal through prose, equations and selected results without publishing an implementation. QuantsPlaybook closes that gap by pairing research papers with executable Python notebooks, giving developers a starting point for inspecting assumptions, reproducing results and testing variations.
From brokerage PDF to backtest
The repository lists more than 100 strategies across market timing, factor construction, quantitative value and portfolio optimization. Entries generally place the original research PDF beside a notebook that applies the methodology to data from JQData or Tushare Pro.
| Research track | Coverage | Examples |
|---|---|---|
| Timing | 25+ | RSRS, QRS, Hilbert-Huang signals, wavelets, VIX construction and ETF intraday momentum |
| Factor construction | 22+ | APM, smart money, idiosyncratic volatility, chip distribution, STR salience and team-coin momentum |
| Quantitative value | 2 | A Piotroski-style FFScore reproduction and an excess-cash-flow screen |
This story is for Pro members
You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.
Comments
