Machine learning in trading: theory, models, practice and algo-trading - page 1904
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
Here, have some fun
bugs on a simple tree
1.0 0.8648648648648649
You can do better than that, good for you.
Hey, that's cool, can you make only two clusters 0 and 1? Is it possible?
Or rather, tell me which cluster is responsible for the flit, I'll just tear it down... I guess 0?
Hey, that's cool, can we have only two clusters 0 and 1? Is that possible?
Or rather, tell me which cluster is responsible for flotation, I'll just tear it down... I take it 0?
I don't know, it's on automatic.
I'll have to write a new one.
If you leave only 2, the model will be more stupid. But in general I do not need, just threw you to play
I don't know, it's on automatic.
You'll have to write a new one.
If you leave only 2, the model will be stupider. But in general I do not need, just threw you to play
Removed class 0 and ran the file in VTRITE. Surprisingly, Maxim, but all the inputs got into the training file. As if there was no peeking in the inputs. Can't be all that rosy unless of course you dumped a dirty file and already cleaned it out. Very surprising :-(
it's like that, but it's not inputs, it's cluster numbers for which you have to do postprocessing later))
this thing writes me ready bot immediately in the terminal folder, and i just press compile button and continue racing in the tester )
it is the same, but these are not inputs but cluster numbers for which you then have to do postprocessing ))
This crap writes the ready bot to me directly into the terminal folder, and I just press the compile button and then run it in the tester )
Let's try again. The first line is the name of your inputs.
How will you tell them apart if you have several of the same ones there?
I ended up numbering them from 1 to 24 + added targeting.
Let's do it again. The first line you have the names of the inputs, right?
How will you distinguish them if you have several of the same?
I ended up numbering them from 1 to 24+ added targeting.
What inputs? 24 signs and a target 'cluster'.
which inputs? 24 signs and the target 'cluster'
Pass number+Difference between the direct estimate function and the hyperbolic function (should decrease)+General generalizability+Last highest generalizability (technical bullshit purely for yourself)
Max you are frankly pissing people off, but first of all yourself. Remember in the market the main thing is not to deceive yourself......
I'm sure you have a 100% peek into the future. Judging by the behavior of the Optimizer, it shows 90% at a single pass in 1 era. How do you explain that?
because this is the data prepared by clustering... everything is already good there