@_zheergen: Earlier, I met a teacher who explained the entire quantitative pipeline very thoroughly. I asked him if there was a single video that could truly string together "data scraping → machine learning prediction → portfolio optimization → strategy backtesting." He showed me a very clear full-stack framework: from environment setup, ARIMA and NeuralProph…
Summary
Introduces a full-stack hands-on Python quantitative trading video tutorial, covering data scraping, machine learning prediction, portfolio optimization, and strategy backtesting, and mentions the open-source quantitative trading execution system Kungfu.
View Cached Full Text
Cached at: 07/27/26, 03:55 PM
Previously, I met a teacher who explained the entire quantitative pipeline in great detail.
I asked him if there was a single video that could truly connect “data scraping → machine learning prediction → portfolio optimization → strategy backtesting.”
He showed me a very clear full-stack framework: from environment setup, ARIMA and NeuralProphet time series forecasting, to QuantStats performance reports, Riskfolio-Lib portfolio optimization, and Backtesting strategy backtesting.
You’d be hard-pressed to find a more complete Python quant introductory tutorial online with a broader toolchain coverage than this.
The video is about 2 hours long and comes with a standalone GitHub repository and a Streamlit interactive app. It genuinely explains the open-source tools commonly used by real quantitative traders in one go.
What’s inside:
- Environment setup and a quick-start to Python / Pandas
- ARIMA stationarity tests, differencing, and forecast evaluation
- QuantStats generates reports on Sharpe ratio, drawdown, heatmaps, and outperforming SPY in one click
- Riskfolio-Lib plots the efficient frontier and maximizes Sharpe weights
- Backtesting implements a dual moving average strategy and outputs complete backtest results
The video also comes with a standalone GitHub repository and a Streamlit interactive app, making it perfect for beginners who want to quickly build a full-stack quantitative knowledge system. I recommend bookmarking it and practicing alongside the code.
爱吃折耳根的Ace (@_zheergen):
This open-source low-latency quantitative trading execution system is basically hitting the top tier.Kungfu is an open-source trading execution system for quantitative traders, focusing on low-latency execution, flexible strategy development, and cross-platform usage.
It provides microsecond-level system response and supports nanosecond-precision timestamps, suitable for trading scenarios with high execution speed requirements.
Key features:
1️⃣ Supports Python and C++
Similar Articles
@_zheergen: I met a veteran quantitative finance expert at PyData who gave a systematic talk on Python's practical use in Quant Finance. I asked him how someone with a math, finance, or physics background can turn Python into a truly efficient quant tool faster. He gave…
A quantitative finance expert systematically explained the practical use of Python in quantitative finance at PyData, covering tools such as NumPy, SciPy, Pandas, Numba, and recommended the open-source library DX Analytics and the resource list awesome-quant.
@geekbb: A Chinese quantitative finance tutorial for absolute beginners, using Jupyter Notebook format, each chapter can be run through in about 30 minutes. The first installment includes 4 chapters: quantitative cognition, return analysis, dual moving average strategy, and strategy backtesting. Uses yfinance to fetch real market data. https://github.c…
A Chinese quantitative finance tutorial for absolute beginners, using Jupyter Notebook format, containing 4 chapters (quantitative cognition, return analysis, dual moving average strategy, and strategy backtesting). Uses yfinance to fetch real data, each chapter can be run through in about 30 minutes.
@KKaWSB: Going the extra mile, folks — quantitative trading projects on GitHub have reached a whole new level. There are plenty of ready-to-use strategies you can practice with (here's a curated list). What Wall Street teams earn millions for is now given to you for free by these open-source projects, complete with tutorials.
A curated list of open-source quantitative trading projects on GitHub, including AI-powered platforms like Qlib and FinGPT, multi-agent frameworks, and backtesting tools, all with tutorials and ready-to-use strategies.
@KKaWSB: https://x.com/KKaWSB/status/2074289438474330306
This article details how to build a personal quantitative trading system using free AI open-source tools (such as OpenBB, Qlib, TradingAgents, etc.), covering five major modules: data, research, backtesting, risk control, and execution, and points out common pitfalls and discipline.
@geekbb: "XQuant: Everyone Can Be a Quantitative Trader" — An Open Source Introductory Manuscript for Quantitative Trading. An open-source introductory manuscript for quantitative trading aimed at beginners, teaching readers to describe strategy ideas in natural language and have AI write the code, building a systematic and iterable quantitative trading system from scratch. https://github.com/xingw…
"XQuant: Everyone Can Be a Quantitative Trader" is an open-source introductory manuscript for quantitative trading aimed at beginners, teaching readers to describe strategy ideas in natural language and have AI write the code, building a systematic quantitative trading system from scratch.