Discussing the article: "Exploring Advanced Machine Learning Techniques on the Darvas Box Breakout Strategy"
Thank you Zhou for the interesting article and code samples . for me I had to manually install some of the Python components to make it work. which may help other users !pip install catboost !pip install onnxruntime !pip install skl2onnx. on completion I can test . but if I try and load the related EA , I have returned 'Failed to set the Output[1] shape Err=5802. I am not sure where this comes from or if it is important and I am unable to work out where this is coming from . . the documentation says ERR_ONNX_NOT_SUPPORTED
5802
Property or value not supported by MQL5 , this is followed by ONNX Model Initialised message ? do you have any suggestions
linfo2 #:
Thank you Zhou for the interesting article and code samples . for me I had to manually install some of the Python components to make it work. which may help other users !pip install catboost !pip install onnxruntime !pip install skl2onnx. on completion I can test . but if I try and load the related EA , I have returned 'Failed to set the Output[1] shape Err=5802. I am not sure where this comes from or if it is important and I am unable to work out where this is coming from . . the documentation says ERR_ONNX_NOT_SUPPORTED
Thank you Zhou for the interesting article and code samples . for me I had to manually install some of the Python components to make it work. which may help other users !pip install catboost !pip install onnxruntime !pip install skl2onnx. on completion I can test . but if I try and load the related EA , I have returned 'Failed to set the Output[1] shape Err=5802. I am not sure where this comes from or if it is important and I am unable to work out where this is coming from . . the documentation says ERR_ONNX_NOT_SUPPORTED
5802
Property or value not supported by MQL5 , this is followed by ONNX Model Initialised message ? do you have any suggestions
Thank you for reminding. The pip install part was ignored but users do have to install the related library if they haven't already.
Your error may be caused by the dimensions used in your model training is different than the ones used in your EA. For example if you trained a model with 5 features, you ought to also input 5 features in your EA, not 4 or 6. A more detailed walk-through is in this article link . Hope this helps. If not, please provide more context.
Utilizing CatBoost Machine Learning model as a Filter for Trend-Following Strategies
- www.mql5.com
CatBoost is a powerful tree-based machine learning model that specializes in decision-making based on stationary features. Other tree-based models like XGBoost and Random Forest share similar traits in terms of their robustness, ability to handle complex patterns, and interpretability. These models have a wide range of uses, from feature analysis to risk management. In this article, we're going to walk through the procedure of utilizing a trained CatBoost model as a filter for a classic moving average cross trend-following strategy. This article is meant to provide insights into the strategy development process while addressing the challenges one may face along the way. I will introduce my workflow of fetching data from MetaTrader 5, training machine learning model in Python, and integrating back to MetaTrader 5 Expert Advisors. By the end of this article, we will validate the strategy through statistical testing and discuss future aspirations extending from the current approach.
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: 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.
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.
This article will dive deep into the features and theory behind three advanced techniques that educators rarely cover, as they’re innovative compared to traditional methods. It will also offer insights into advanced topics like feature engineering and hyperparameter tuning during the model training process. However, it won’t cover every step of the machine learning model training workflow in detail. For readers curious about the skipped procedures, please check this article link for the complete implementation process.
Author: Zhuo Kai Chen