Machine learning in trading: theory, models, practice and algo-trading - page 1655
![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
My teacher -
The forgotten past - the arrows...
Enlighten me...
The transformation and its prediction. Are there any correlations with the initial time.
How much. Whether it's worth the cost...
In order not to mislead, I confess that what I am doing now has nothing to do with the post that you quoted.
Now on the subject of the post... What I used to do.
An elementary trading system based on the intersection of two bars (I don't even know why I chose it)
We go to history and find out which wave periods will be the best in the next 10 or 20 bars(I don't remember) in terms of profitability. We save these periods in a vector.
So we have the values of "ideal parameters", the chart, as I remember, was more stationary than not, I didn't train AMO (it hadn't occurred to me then), but it is definitely possible and will definitely work better than with prices because: I applied spectrum analysis to the obtained chart and saw a strong dependence on price volatility(which is basically obvious), and as you and I know volatility is very easy to forecast. It turns out that volatility forecasting may turn out to be a great feature for AMO forecasting "an ideal period".
In order not to mislead, I confess that what I am doing now has nothing to do with the post that you quoted.
Now on the subject of the post... What I used to do.
An elementary trading system based on the intersection of two bars (I don't even know why I chose it)
We go to history and find out which wave periods will be the best in the next 10 or 20 bars(I don't remember) in terms of profitability. We save these periods in a vector.
So we have the values of "ideal parameters", the chart, as I remember, was more stationary than not, I didn't train AMO (it hadn't occurred to me then), but it is definitely possible and will definitely work better than with prices because: I applied spectrum analysis to the obtained chart and saw a strong dependence on price volatility(which is basically obvious), and as you and I know volatility is easy to predict. It turns out that predicted volatility may turn out to be an excellent feature for AMO predicting "an ideal period".
Let's put it this way. Let's say the exact value of future volatility is not easy to predict, unlike the future volatility sign.
1. What do you use to predict volatility?
2. I think there is a good reason for that. I mean to use future volatility as one of the system inputs.
Some people even promote JPrediction_v15.0. What kind of people there are now. Right?
I had no doubt that you would mention him, as if "as a joke", eh Yura, Yura... He has gone completely feral, does not communicate with people, has ceased to understand the subtleties of human psychology, he cuts off his shoulders.
I had no doubt that you would mention him, as if "as a joke", eh Yura, Yura... He has gone completely feral, does not communicate with people, has ceased to understand the subtleties of human psychology, cuts off his shoulders.
I had no doubt that you would mention him, as if "as a joke", eh Yura, Yura... He has gone completely feral, does not communicate with people, has ceased to understand the subtleties of human psychology, cuts off his shoulders.
Innokenty, don't bullshit. Misha is Misha, Yura is Yura, God rest his soul...
ok
Innokenty, don't bullshit me. Misha is Misha, Yura is Yura, God rest his soul...
Innokenty, don't bullshit. Misha is Misha, Yura is Yura, God rest his soul.
Well, yes, if it were all right with him there would be the 20th version by now, not my pathetic semblance. May he rest in peace..... Too bad :-(
No shit no shit, that's what I believed, it's all made up, Jura thinks he's a rock star like Elvis and thinks that death is the best PR, but he's far from Elvis, he's more like an attacking leader.