The traditional way to backtest or develop strategies is to take a very long history and run your rules over that history. The objective is to find rules that produce stable or consistent returns. However, I have recently been experimenting with another technique for developing intraday strategies where I load from only a single to a few days worth of history. On this short history, I seek to find the optimal trading rules or discover patterns. My original objective was simply to find rules, filters, or patterns that might be helpful to understand as a discretionary trader.
However, surprisingly, some of the rules I developed continued to perform when I extended my backtest history as far as 5 years back, the maximum that I checked. I am not sure how useful this approach will prove to be but it looks like it may be useful as a starting point given that it is especially difficult to develop systematic intraday trading strategies.
Curtis is passionate about markets. He has developed top ranked futures strategies. His core focus is (1) applying machine learning and developing systematic strategies, and (2) solving the toughest problems of discretionary trading by applying quantitative tools, machine learning, and performance discipline.
Please log in again. The login page will open in a new window. After logging in you can close it and return to this page.