Machine learning in trading: theory, models, practice and algo-trading - page 1352
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
If I knew, I would not have asked for help here.
In general, the story with the appearance of this file in my possession is unclear. I do not understand the motives and goals of the person who sent it. But it would be very foolish not to investigate it. IMHO.
Then there will be a question "how to make money on such a row" )))
If I knew, I would not have asked for help here.
In general, the story with the appearance of this file in my possession is unclear. I do not understand the motives and goals of the person who sent it. But it would be very foolish not to investigate it. IMHO.
Did the equity chart come with this file?)
No
No
and it's not good to cheat))
https://www.mql5.com/ru/forum/221552/page985#comment_10703130
In addition to the posthttps://www.mql5.com/ru/forum/86386/page1344#comment_10678027 about predicting random processes.
Now it's the same, we use a neural network to predict LF filter value on real market data. Prediction interval - 5 min on 1 m TF.
All values are in conventional units on the scale of NS data, of course, they can be recalculated into real values.
With prediction values < -(3-4) or > (3-4) you may work in a real TS. It won't go in the opposite direction.
Do I understand correctly that you've noisy quotes and managed to detect this noise on market data?
No
In general, pay attention to how many digits after the comma there - is this some kind of nonsense, or has already been processed by something data 1.087139964
Am I correct in assuming that you have made a noise in the quotes and were able to detect this noise in the market data?
No. This is a prediction of the output of the VLF on the market BP without any change, and comparing it to the real value. The sample is the same as before, 5000.
I've added there the graph of 10 min forecast.
No. This is a prediction of the output of the LPF on the market BP, without any changes, and comparing it to the real value. The sample is the same - 5000.
Here's a silly question. What was the input to the low-pass filter? And how could it be used? I just had a feeling, that network described low pass filter's work...
And earlier I asked about boosting, didn't you try it on it?and it's not good to cheat))
https://www.mql5.com/ru/forum/221552/page985#comment_10703130
Well, this citizen talked a lot and vaguely... The main purpose of his message was that nothing will help me: neither Erlang, nor Bachelier, nothing at all, except such rows, which he gave.
Nothing works on my models, that's why I came here, maybe a neural network will see something.
Here's a silly question. What was the input to the low-pass filter? And how can it be used? It just feels like the network described the operation of this LPF...
And earlier I asked about boosting, have you tried it?Market BP was fed to the HPF input. The same HP was fed to the NS input. Yes, that's right, the network described the operation of the LPF and made a prediction of its output at a given interval.
Not at boosting, I haven't tried it.