Discussing the article: "Reimagining Classic Strategies (Part 15): Daily Breakout Trading Strategy"
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Reimagining Classic Strategies (Part 15): Daily Breakout Trading Strategy.
Human traders had long participated in financial markets before the rise of computers, developing rules of thumb that guided their decisions. In this article, we revisit a well-known breakout strategy to test whether such market logic, learned through experience, can hold its own against systematic methods. Our findings show that while the original strategy produced high accuracy, it suffered from instability and poor risk control. By refining the approach, we demonstrate how discretionary insights can be adapted into more robust, algorithmic trading strategies.
As we have already stated, we typically use machine learning algorithms to help us learn relationships that project the past onto the future. However, we almost always assume such a relationship exists and can be learned from the data. We rarely take the time to prove that these relationships exist in the first place. Discretionary traders, by necessity, have essentially been forced to look for reliable relationships that could sustain their careers. From this perspective, we could argue that human traders were forced to do the manual labor that can set the foundation for our machine learning models to build on.
We therefore seek to bridge the gap between machine learning and financial trading by using the heuristics and rules of thumb that human beings have developed over many years of interaction with the markets. These rules, which traders have generally learned to abide by, may serve as a framework that enables our models to learn financial markets in a more structured way. Instead of having our models prove relationships from scratch, we can extend principles that have already been proven valid over time. This gives our models a head start rather than asking them to begin at rest.
The most important part of our test is proving the validity of the strategy we begin with. For this reason, our trading strategy was based on a well-known breakout approach that relies on the relationship between consecutive trading days. The strategy in essence is rather simple.
On the beginning each trading day, we begin by marking the prior day’s high and low.
Author: Gamuchirai Zororo Ndawana