This is the beginning of a three part series that I completed towards the end of 2017 as a learning module for Quantinsti.com. The purpose of the series is to demonstrate a research workflow focused around the theory and application of mixture models as the core framework behind a algorithmic trading strategy. Below is a quote taken from the README of the github repo:
“The primary goal of this repo is to demonstrate the workflow between research of a quantitative idea or theory to implementation as a potential live trading strategy. Unlike other finance based tutorials the results will not be cherry picked to show only the best of the best examples. Sometimes results are counterintuitive, sometimes they are conflicting. Real strategy development is often dirty, complex, full of starts and stops and requires us to use all of our skills to extract the signal from the noise. With that said I welcome interactive engagement, ideas, insight, and constructive criticism, especially if errors or bugs are found.”
I will be presenting each of the notebooks on the blog although you can feel free to read ahead by visiting the github repo directly. What is new however is that at the end of three part series I will be publishing a Part 4 where I will describe an actual implementation of the strategy and release the code for the actual algorithm for my readers to dissect, alter, and experiment with on the Quantconnect.com platform.
Be on the lookout for the brand new Part 4 - Algorithm Implementation.