Something Interesting - page 56

[Sergey Golubev]

Exploring Advanced Machine Learning Techniques on the Darvas Box Breakout Strategy

The Darvas Box Breakout Strategy, created by Nicolas Darvas, is a technical trading approach that spots potential buy signals when a stock’s price rises above a set "box" range, suggesting strong upward momentum. In this article, we will apply this strategy concept as an example to explore three advanced machine learning techniques. These include using a machine learning model to generate signals rather than to filter trades, employing continuous signals rather than discrete ones, and using models trained on different timeframes to confirm trades. These methods offer fresh perspectives on how machine learning can enhance algorithmic trading beyond traditional practices.