Machine learning in trading: theory, models, practice and algo-trading - page 1630
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
Hmm, and the predictions on the training data, as well as the recognition on the test data, did you also spread/narrow ? or was there a fixed label
yes, in proportion to the size of the pattern type... me and the guy did it about 10 years ago ) in a different way. Then I tried it another way and it sucked too.
Yes, in proportion to the size of the pattern type... me and the guy did it about 10 years ago) in different ways. Then I tried it in another way, and it sucked too.
don't upset me... I already have doubts about my idea))
Shit... don't upset me... I'm already doubting my idea))
Try it... but keep it simple, it either works or it doesn't. All this trickery is just brainwashing.
Well, you try it... but you better keep it simple, it either works or it doesn't. All that trickery is just brainwashing.
Look at my question on the SA, maybe you know how to do it.
See my question I asked in SA, maybe you know how to do it.
You don't. You have to take a long series and highlight the trend, residuals, seasonal components, etc. And don't f... don't fuck with your brain
Everything new is well forgotten old...
The same MGUA in action, 1960)
_________________________________________
Can someone help me with the answer to my question, and I'm stuck and dumb
https://ru.stackoverflow.com/questions/1097982/%D0%BF%D0%B5%D1%80%D0%B5%D0%BD%D0%BE%D1%81-%D0%B0%D0%B1%D1%81%D0%BE%D0%BB%D1%8E%D1%82%D0%BD%D1%8B%D1%85-%D0%B7%D0%BD%D0%B0%D1%87%D0%B5%D0%BD%D0%B8%D0%B9-%D0%B2-%D0%BE%D0%B1%D0%BB%D0%B0%D1%81%D1%82%D1%8C-%D0%BD%D0%BE%D1%80%D0%BC%D0%B8%D1%80%D0%BE%D0%B2%D0%B0%D0%BD%D0%BD%D1%8B%D1%85-%D0%B7%D0%BD%D0%B0%D1%87%D0%B5%D0%BD%D0%B8%D0%B9-%D0%B8-%D0%BE%D0%B1%D1%80%D0%B0%D1%82%D0%BD%D0%BE
Or can you just help, click this button to raise it in the top please
You can't submit increments?
The first sign of fuflomecin. Neron nets are a universal tool, if the methodology of model preparation is correct, it should work everywhere. Somewhere worse, somewhere better, but definitely work. And if you see that for some instrument the results are coordinately bad, it means that something is wrong ..... And after some time, it will stop working on bitcoin, and start working on francs. As an example. But in general, it is not good :-(
It shouldn't, it depends on the pair and the timeframe. It depends because these parameters change "technicality", i.e. the possibility to detect repetitive working patterns. One and the same method of choosing input parameters gives acceptable quality level of prediction in one case, and unacceptable one in another case. If you've tried trading, you know that the analysis at one hour is very different from the analysis at one minute, and that eurusd is not like brent.
It should not, it depends on the pair and the timeframe. It depends because these parameters change the "technicality", i.e. the ability to detect repetitive working patterns. One and the same method of choosing input parameters gives acceptable quality level of prediction in one case, and unacceptable one in another case. If you tried trading, you know that 1 hour movement is very different from 1 minute movement and that eurusd is not similar to brent.
I think that the problem lies in the input data. I, for example, have a collecting algorithm that, I'm sure, allows me to work with any instrument and timeframe. But if the required data is missing for a quote, such as Bitcoin, then there is nothing I can do about it. Maybe my method won't work on Bitcoin...
It can not be, it seems that you are not at all in the subject.