This is the code repository for Python for Algorithmic Trading Cookbook, published by Packt.
Recipes for designing, building, and deploying algorithmic trading strategies with Python
Discover how Python has made algorithmic trading accessible to non-professionals with unparalleled expertise and practical insights from Jason Strimpel, founder of PyQuant News and a seasoned professional with global experience in trading and risk management. This book guides you through from the basics of quantitative finance and data acquisition to advanced stages of backtesting and live trading. Detailed recipes will help you leverage the cutting-edge OpenBB SDK to gather freely available data for stocks, options, and futures, and build your own research environment using lightning-fast storage techniques like SQLite, HDF5, and ArcticDB. This book shows you how to use SciPy and statsmodels to identify alpha factors and hedge risk, and construct momentum and mean-reversion factors. You’ll optimize strategy parameters with walk-forward optimization using VectorBT and construct a production-ready backtest using Zipline Reloaded. Implementing all that you’ve learned, you’ll set up and deploy your algorithmic trading strategies in a live trading environment using the Interactive Brokers API, allowing you to stream tick-level data, submit orders, and retrieve portfolio details. By the end of this algorithmic trading book, you'll not only have grasped the essential concepts but also the practical skills needed to implement and execute sophisticated trading strategies using Python.
This book covers the following exciting features:
- Acquire and process freely available market data with the OpenBB Platform
- Build a research environment and populate it with financial market data
- Use machine learning to identify alpha factors and engineer them into signals
- Use VectorBT to find strategy parameters using walk-forward optimization
- Build production-ready backtests with Zipline Reloaded and evaluate factor performance
- Set up the code framework to connect and send an order to Interactive Brokers
If you feel this book is for you, get your copy today!
All of the code is organized into folders.
The code will look like the following:
import datetime as dt
import pandas as pd
from openbb_terminal.sdk import openbb
Following is what you need for this book: Python for Algorithmic Trading Cookbook equips traders, investors, and Python developers with code to design, backtest, and deploy algorithmic trading strategies. You should have experience investing in the stock market, knowledge of Python data structures, and a basic understanding of using Python libraries like pandas. This book is also ideal for individuals with Python experience who are already active in the market or are aspiring to be.
With the following software and hardware list you can run all code files present in the book (Chapter 1-13).
| Chapter | Software required | OS required |
|---|---|---|
| 1-13 | Python version 3.10 | Windows, Mac OS X, and Linux (Any) |
| 1-13 | PostgreSQL | Windows, Mac OS X, and Linux (Any) |
| 1-13 | OpenBB Platform version 4+ | Windows, Mac OS X, and Linux (Any) |
| 1-13 | pandas version 2+ | Windows, Mac OS X, and Linux (Any) |
Jason Strimpel is the founder of PyQuant News and co-founder of Trade Blotter, with a career spanning over 20 years in trading, risk management, and data science. He previously traded for a Chicago-based hedge fund, served as a risk manager at JPMorgan, and managed production risk technology for an energy derivatives trading firm in London. In Singapore, Jason served as the APAC CIO for an agricultural trading firm and built the data science team for a global metals trading firm. He holds degrees in finance and economics and a Master’s in quantitative finance from the Illinois Institute of Technology. His career has taken him across America, Europe, and Asia. Jason shares his expertise through the PyQuant Newsletter, social media, and teaches the course "Getting Started With Python for Quant Finance."