My latest series is Python for Finance, which makes heavy use of Quantopian.
I start the series off with a simplistic introduction to using Python + Pandas + Matplotlib to get stock data, visualize stock data, and to manipulate this data. This is all done locally, just to get us comfortable with tools that we’re going to use on Quantopian.
From here, we get into Quantopian for building, researching, and analyzing trading strategies.
If you would like to check it out, the series starts here: Python for Finance introduction
If you are already familiar with Pandas and want to jump straight into the strategies and using Quantopian for back-testing and research: Algorithmic trading and research with Quantopian
Table of Contents for the Quantopian-specific content:
- Testing trading strategies with Quantopian. Platform Introduction
- Placing an Order
- Schedule Function
- Research Introduction
- Alphalens for analyzing Factors
- Backtesting Alpha Factors
- Coming up with a more realistic strategy
- Finding multiple alpha factors
- Combining alpha factors
- Portfolio Optimization with Optimize API
Part 1 through 3 are for a basic algorithm introduction.
Part 4-8 cover more of the research and strategy basics side of things, using a slightly modified version of Jamie McCorriston’s “How to Get an Allocation: Writing an Algorithm for the Quantopian Investment Management Team” webinar code.
Part 9 through 12 cover more of a typical workflow for devising a multi-factor trading strategy.
The respective notebooks are available for download individually per tutorial, and sample code is all posted. I have gone ahead and attached the most instructive notebook from the series (from parts 4-8), but this notebook does not cover any of the algorithms, nor does it cover part 9-12 where we actually go through and find a few factors, test those, combine those, test those, use optimize API...etc.
If you have any questions, comments, or suggestions, feel free to leave them below.