Blog

Explore the research behind our trading, plus some just-for-fun stuff....

Posted on May 10, 2016 by Kris Longmore
44 comments.
8,552 Views

Introduction My first post on using machine learning for financial prediction took an in-depth look at various feature selection methods as a data pre-processing step in the quest to mine financial data for profitable patterns. I looked at various methods to identify predictive features including Maximal Information Coefficient (MIC), Recursive Feature Elimination (RFE), algorithms with built-in feature selection, selection via...

Posted on Apr 14, 2016 by Kris Longmore
6 comments.
1,826 Views

Disclaimer: I am not posting this at the behest of the developers of Zorro, nor do I receive any form of payment or commission for this post. I felt that I should relay this experience because it was an example of customer service that went way above and beyond the call of duty in terms of its promptness and professionalism. Credit where...

Posted on Mar 04, 2016 by Kris Longmore
72 comments.
21,461 Views

Updates 2019: In this first Machine Learning for Trading post, we've added a section on feature selection using the Boruta package, equity curves of a simple trading system, and some Lite-C code that generates the training data. Don't forget to download the code and data used throughout the Machine Learning for Trading series. Way back in the day when I...

Posted on Feb 04, 2016 by Kris Longmore
22 comments.
9,798 Views

Recently, I wrote about fitting mean-reversion time series analysis models to financial data and using the models' predictions as the basis of a trading strategy. Continuing our exploration of time series modelling, let's research the autoregressive and conditionally heteroskedastic family of time series models. In particular, we want to understand the autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional...

Posted on Jan 02, 2016 by Kris Longmore
27 comments.
7,935 Views

In the first Mean Reversion and Cointegration post, I explored mean reversion of individual financial time series using techniques such as the Augmented Dickey-Fuller test, the Hurst exponent and the Ornstein-Uhlenbeck equation for a mean reverting stochastic process. I also presented a simple linear mean reversion strategy as a proof of concept. In this post, I’ll explore artificial stationary time series...

Posted on Dec 03, 2015 by Kris Longmore
29 comments.
7,277 Views

This series of posts is inspired by several chapters from Ernie Chan's highly recommended book Algorithmic Trading. The book follows Ernie's first contribution, Quantitative Trading, and focuses on testing and implementing a number of strategies that exploit measurable market inefficiencies. I'm a big fan of Ernie's work and have used his material as inspiration for a great deal of my own research. My...

Posted on Nov 24, 2015 by Kris Longmore
5 comments.
409 Views

Important preface: This post is in no way intended to showcase a particular trading strategy. It is purely to share and demonstrate the use of the framework I've put together to speed the research and development process for a particular type of trading strategy. Comments and critiques regarding the framework and the methodology used are most welcome. Backtest results presented are...

Posted on Nov 15, 2015 by Kris Longmore
22 comments.
2,066 Views

In the last article, I described an application of the k-means clustering algorithm for classifying candlesticks based on the relative position of their open, high, low and close. This was a simple enough exercise, but now I tackle something more challenging: isolating information that is both useful and practical to real trading. I'll initially try two approaches: Investigate whether there are...