data mining

Posted on Mar 04, 2016 by Kris Longmore

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 first got into the markets, one of the first books I read was David Aronson's Evidence Based Technical Analysis. The nerdy engineer in me was hooked by the 'Evidence Based' part. This was soon after I had digested a trading book claiming a basis in chaos theory (a link which turned out to be BS). Apparently, using complex-sounding terms in trading book titles lends a boost of credibility.... and book sales. I'm a victim of marketing. Evidence Based Technical Analysis promotes a scientific approach to trading, including a detailed method for the assessment of data-mining bias in your backtest results. There's also a discussion around the reasons why many traders embrace subjective beliefs over objective methods. Having seen this first...