Machine learning in trading: theory, models, practice and algo-trading - page 1117
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
Actually the opposite is true...
Better a worse algorithm but more examples than a cool algorithm but less data.
Even 1000 is not enough, especially for the market...
All right, since you're new, I'll explain it to you separately...
40 examples of my sample is about a month of work on the TF M15. What's wrong with training a model for one month so it works in profit at least for 2 weeks. There is no grail and weekly optimization is quite normal, let alone optimization once every two weeks.
But Maksimka trains his models for a year or more and he is not shining with the result ....
Not bad results in predictive ability will NOT lead to stable models, because simply ridiculous number of observations = 51. We need at least 10 times as many, or better, 100 times as many.
SanSanych, explain to a fool why a classifier needs predictive power?
Not bad results in predictive ability will NOT lead to stable models, because simply ridiculous number of observations = 51. We need at least 10 times as many, or better, 100 times as many.
If you build models on that number of observations, the results are abysmal.
Predicted
Actual [0,0] (0,1] Error
[0,0] 42.9 28.6 40
(0,1] 28.6 0.0 100
Overall error: 57.1%, Averaged class error: 70%
Rattle timestamp: 2018-10-18 21:29:39 user
======================================================================
Error matrix for the Linear model on Mic1.txt [validate] (counts):
Predicted
Actual [0,0] (0,1) Error
[0,0] 1 4 80
(0,1] 2 0 100
Error matrix for the Linear model on Mic1.txt [validate] (proportions):
Predicted
Actual [0,0] (0,1] Error
[0,0] 14.3 57.1 80
(0,1] 28.6 0.0 100
Overall error: 85.7%, Averaged class error: 90%
Rattle timestamp: 2018-10-18 21:29:39 user
======================================================================
Error matrix for the Neural Net model on Mic1.txt [validate] (counts):
Predicted
Actual [0,0] (0,1) Error
[0,0] 2 3 60
(0,1] 1 1 50
Error matrix for the Neural Net model on Mic1.txt [validate] (proportions):
Predicted
Actual [0,0] (0,1] Error
[0,0] 28.6 42.9 60
(0,1] 14.3 14.3 50
Overall error: 57.1%, Averaged class error: 55%
Rattle timestamp: 2018-10-18 21:29:39 user
I hope you're not trying to predict the exit???? It is already predicted, you just need to get as close to it as possible. There is no need to predict it....
What is AI?
Artificial Intelligence.
Sanych, what about the results of the test??? How does the model behave there???
By the way, if you use Rattle, it is better not. I can run it myself.... interesting to see results on your secret AI models :-)
Artificial Intelligence.
А,... Are you already using AI? And we all are sitting on the AI.
А,... Are you already using AI? And we're all sitting on AI.
I'm surprised by your ignorance in this matter. It's the same thing. MO = AI Machine Learning = Artificial Intelligence.
I am surprised at your ignorance on this subject. It's the same thing. ME=Machine Learning=Artificial Intelligence.
Wow. Who would have thought? Actually these are completely different things.
That's amazing. Who would have thought? Actually, it's completely different.
What's the difference? Enlighten....
hilarious... more!))
So what do you think about the data?
That's amazing. Who would have thought? Actually, they are completely different things.
Not really different, it's evolution of machine learning, from Assembler to Python, so to speak ;)
https://habr.com/post/401857/