Using neural networks in trading - 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
It's an interesting topic. I've been doing it myself, but I haven't got any results. The future bars do not depend much on the history (I mean they do, but they are VERY weak). The future bars are influenced by two factors - placement of large orders and news. A neuronet cannot predict this. And in conditions of a "dead market" (no news, no large operations) reliable forecasts are possible. But the occurrence of such a situation cannot be predicted either.
I already have an impression, that it is the huge mass of players on Forex that kills all appearing regularities, on which one can earn, and not some "dummy". And if so, the market can only be approached statistically. It is impossible to predict the movement of an individual molecule in a gas. But the gas itself obeys strict laws in a closed volume. That's what I'm doing now :)
It's an interesting topic. I've been doing it myself, but I haven't got any results. The future bars do not depend much on the history (I mean they do, but they are VERY weak). The future bars are influenced by two factors - placement of large orders and news. A neuronet cannot predict this. But in conditions of a "dead market" (no news, no large operations) reliable forecasts are possible. But the occurrence of such a situation also cannot be predicted.
I already have an impression, that it is the huge mass of players on Forex that kills all appearing regularities, on which one can earn, and not some "dummy". And if so, the market can only be approached statistically. It is impossible to predict the movement of an individual molecule in a gas. But the gas itself obeys strict laws in a closed volume. That's what I am doing now :)
What about https://www.mql5.com/ru/code/10755 ? How about finding a pattern?
And about news and other factors. Weren't there any news at the last bars? And the participation of big players?
Take, for example, the Euromarket (forecasts, consequences)... There is a lot of wave analysis. Isn't it a task for a neural network?
It's an interesting topic. I've been doing it myself, but I haven't got any results. The future bars do not depend much on the history (I mean they do, but they are VERY weak). The future bars are influenced by two factors - placement of large orders and news. A neuronet cannot predict this. But in conditions of a "dead market" (no news, no large operations) reliable forecasts are possible. But the occurrence of such a situation also cannot be predicted.
I already have an impression, that it is the huge mass of players on Forex that kills all appearing regularities, on which one can earn, and not some "dummy". And if so, the market can only be approached statistically. It is impossible to predict the movement of an individual molecule in a gas. But the gas itself obeys strict laws in a closed volume. This is what I am doing now :)
This is a sensible idea.
However, there is no need to pin your hopes on the neural networks in order to implement it in your Expert Advisor.
The only problem is that the majority of local regulars do not understand them and do not know how to use them.
Very much needed. Without feelings, there is no intelligence. Suppose we created a robot capable of seeing and recognising objects, hearing and understanding speech, moving its arms and legs, etc. Turn on the ON button and ... Question to all. What will this robot do after it is turned on?
Is there a lot of indicator, air ige traded
DhP:
Be patient.
I will publish it in 2 months.
---------------------------------------------------------------------------------------------------------------------------
Where is it published? Or has it not been 3 years yet?
There was a link to monitoring in my profile for six months. There were results, but I wasn't interested in them.
The idea ended its life ignominiously. )))
There was a link to monitoring in my profile for six months. There were results, but I wasn't interested in them.
The idea ended its life ignominiously. )))
I hope the new ideas turned out to be more productive?)
I hope the new ideas turned out to be more productive?)
Ideas replace one another. A perpetual search. Just being a programmer is not enough.
I hope the new ideas are more productive) .
Ideas alternate with each other. It's a never-ending search. Just being a programmer is not enough.
This is basically what successful trading is based on, in terms of trading robots?