Discussing the article: "Creating a mean-reversion strategy based on machine learning" - page 5
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
Added all the basic attributes from the pandas module.
https://pandas.pydata.org/docs/reference/window.html
As a result, I got this graph. Maxim, thank you for your labour.
Yes, attributes can affect models in different ways, along with markup. It makes sense to experiment with them too. The main thing to check is that there is no hidden peeking. It's definitely not in the article. You're welcome.
Yes unfortunately there was that very peek on my graph. It can be easily checked on completely random data.
Generate a time series using the random module, if there is a smooth line on oos, there is 100% peeking
Fifteen years of 50% profit?
Generate a time series using the random module if there is a smooth line on oos, that is peeking 100%
Good test.
Everything is so much more reliable when there is a transfer mechanism to MT5-Tester.
All such are more reliable when there is a transfer mechanism to MT5-Tester.
Of course, there is no such thing as a lot of checks.
In the condition, when a new cluster appears, the open order is closed? That is, the trades do not overlap? Right?
In the condition, when a new cluster appears, the open order is closed? That is, the trades do not overlap? Right?
Example of market modes. If an order opened on yellow, will the order be closed when the mode changes to red?
This is very important, because the trend has already changed, and in your script it may be written in the condition to expect a stop loss