Discussion of article "Advanced resampling and selection of CatBoost models by brute-force method" - page 3
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
Can you drop a link to Jupyter Notebook with this source code in Colab?
That's why I lack statistical information, let's say we studied 1000 models and 5% of them showed a good profit since 2015, but we also need to evaluate the similarity of models among themselves, which is more difficult, but more informative.
Globally, I still lack power, I have algorithms, but I do not have enough power to look at all the instruments from 70 years on the minutes.
You can export to colaba, the file is at the bottom of the article
Converted to notebook: https://colab.research.google.com/drive/1AsTG8uaRnIc1sjz3WOOUr7F8rFq_N9wA?usp=sharing
But no way to import MT5, tried all options, none of them loaded repository https://pypi.org/project/MetaTrader5.
!pip install MetaTrader5 with this command errors
Could not find a version that satisfies the MetaTrader5 requirement (from versions: none )
No matching distribution found for MetaTrader5
There's no difference, you can check. I just like it better this way.
I can't. If someone checks it out, it would be interesting to see.
So there is an oversampling - the purpose of which is to find those patterns in 2020, which were in effect for the entire period - since 2015. Theoretically, it may be necessary to brute force more, but the goal will be achieved, the other thing is that it is not clear whether it is a pattern or a fitting, and without even a hypothetical answer to this question, it is difficult to make a decision on the expediency of installing the TC on the real....
Read:
The last (right) part of the chart (about 1000 trades) is a training dataset from the beginning of 2020, while the remaining part is new data that did not participate in the model training.
Converted to notebook: https://colab.research.google.com/drive/1AsTG8uaRnIc1sjz3WOOUr7F8rFq_N9wA?usp=sharing
But no way to import MT5, tried all options, none of them loaded the repository https://pypi.org/project/MetaTrader5.
!pip install MetaTrader5 with this command errors
Could not find a version that satisfies the MetaTrader5 requirement (from versions: none )
No matching distribution found for MetaTrader5
and it won't work, because it's linux and the terminal won't fit there
as an option, download already prepared files with quotes
and it won't work because it's linux and terminal won't fit.
Alternatively, you can download already prepared files with quotes
That's what I understood, thanks for the answer.
Reading:
The last (right) part of the chart (about 1000 trades) is a training dataset from the beginning of 2020, while the rest of the chart is new data that was not involved in the training of the model in any way.
Is not looking for patterns in the future, but looking for dependencies in a series. The sequence is not important. You can look in the middle and test front and back, it won't change anything
it's so simple to understand that it doesn't require further explanation.
The advantage is that the pattern found may fade over time. In this case, learning from recent data is preferableis not to look for patterns in the future, but to look for dependencies in a series. The sequence is not important. You can search in the middle and test front and back, it won't change anything
it's so simple to understand that it doesn't require further explanation.
the advantage is that the pattern found may fade over time. In this case, learning from recent data is preferable
This is not an abstract series. There are obvious "dependencies" (the same word, but the meaning is different for understanding) from left to right (from the past to the future), but not vice versa. There are hardly any scientific publications on quote forecasting, where they would do tests on the past.