Machine learning in trading: theory, models, practice and algo-trading - page 3550
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
I'm chillin'. It's gotten worse. Basically if you subtract the return with any lag from the prices, you get roughly the same model. So you're just taking something away from the original prices.
I'm telling you for the third and last time.)
Where are your conclusions? At least do a backtest :)
A backtest is when you already have a complete robot.
Ohh. Okay.
all by myself, all by myself.
a backtest is when there's already a full-fledged robot.
Ohh. Okay.
all by myself, all by myself.
Yeah, except we have different models, but you think they're the same.
Yeah, I've gone through a few. Mashka + returnee, no short mashka, a few returnees. Everything is worse. But it works on new data, but not very well.
You have to make a paternion on the model candles, you didn't do that and you didn't even make candles.
Wrote a monster that builds 2 level clustering and looks for profitable clusters.
Finds all sorts of interesting TCs
The log is just as inadequate. You can see that he finds either a good TC or nothing :)