Discussing the article: "Neural Networks in Trading: Hierarchical Vector Transformer (Final Part)"

[MetaQuotes]

Check out the new article: Neural Networks in Trading: Hierarchical Vector Transformer (Final Part).

We continue studying the Hierarchical Vector Transformer method. In this article, we will complete the construction of the model. We will also train and test it on real historical data.

The training continues until the model's error stabilizes at a certain level. At which point further dataset updates no longer contribute to optimizing the Actor's policy.

We evaluate the effectiveness of the trained model using the MetaTrader 5 strategy tester, applying historical data from January 2024, while keeping all other parameters unchanged. The results of the trained model's testing are presented below.

Author: Dmitriy Gizlyk