Machine learning in trading: theory, models, practice and algo-trading - page 477
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
This is what I was able to achieve on the test data. The network is running on the indicators macd, atr, stochastic. Indicator parameters are by default. There are practically no false signals. Yellow dots are network operation. But the network misses signals. I need some ideas on the choice of indicators and their parameters.
Heartfelt, heartfelt! Now I really felt the help from you ... :-)
Teacher, it's you (us) Composter helped (the author of the script). And I helped you at the 4th forum, offering to throw a rattle, you just have not understood))))
This is what I was able to achieve on the test data. The network is running on the indicators macd, atr, stochastic. Indicator parameters are by default. There are practically no false signals. Yellow dots are network operation. But the network misses signals. I need some ideas on the choice of indicators and their parameters.
This is what I was able to achieve on the test data. The network is running on the indicators macd, atr, stochastic. Indicator parameters are by default. There are practically no false signals. Yellow dots are network operation. But the network misses signals. I need some ideas on the choice of indicators and their parameters.
Yes, it passes through, so let it pass.
A picture of the output of the trained NS on the test.
And this is the result of the test, a screen copy
97- total amount of deals
91 - successful trades
6 - failed trades (6 out of 97, Carl!)
0.938...-the fraction of successful trades.
Missed (did not notice at all) about half. Let's consider that I went to lunch.)
This is what I was able to achieve on the test data. The network is running on the indicators macd, atr, stochastic. Indicator parameters are by default. There are practically no false signals. Yellow dots are network operation. But the network misses signals. I need some ideas on the choice of indicators and their parameters.
(Bummer!))
The gruel has been found.
Yep, it misses, so be it.
A picture of the output of the trained NS on the test.
And this is the result of the test, a copy of the screen
97- total amount of deals
91- successful deals
6 - failed trades (6 out of 97, Carl!)
0.938...-share of successful trades.
Missed (did not notice at all) about half. Let's consider that I went to lunch.)
Teacher, it helped you (us) Composter (the author of the script). And I helped you on 4 forum, suggesting to throw out the rattle, you just have not yet understood))))
Nah... she's okay.... If it does that to my data, I'm afraid to imagine what your NS will do to my data :-)
Please help a little more and I will be grateful to you!!!!!
I wrote an indicator, but it does not want to work in real time. It calls the basic indicator, makes its own calculation, and adds arrows on the chart. As soon as there is a new bar, I have to switch the TF to update the arrows and it takes an awfully long time.... See what is wrong, but I will tell you what it does.....
And it does the following.....
I once wondered what a trader who has a working robot should do, but he sits all day on the market, like monitoring..... BORING!!!!! And for the fun of it, I decided to make such an amusement......
"Binary Options", yes yes you are not mistaken, skeptics will say, well, here we go.... The ignorant will try to sass me, etc. Well, I'll answer.... Well what about???? What to do when the window began to form? Boring!!!! The advisor will work out the signal itself..... Why not chop in BO, while the window is forming????
As a result, from 5 bonus points in alps, 4 trades+. series goes so far +6, -1,+1.
It looks something like this.....
where the up arrow says that the next bar will be up, the down arrow - down!
As you can see there is only one mistake.... And the main advantage is that we analyze not the whole market, but only bars in the window, and these arrows do not want to be displayed online ... That's what I'm asking in the previous post....
This stats says nothing, 91 good for 1 point and 6 bad for a loss of deposit can be for example :Z
He doesn't.) Anything can happen, of course.) All right.
5328 -net profit
5391 -total profit in trades
-63 - total loss in trades.
0.988 - efficiency (5328/5391).
Is that what it says? )) Or doesn't it also?)
But this is a test of the same NS on other data.