Machine learning in trading: theory, models, practice and algo-trading - page 3583
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
I don't use it myself.
There are some doubts about solving trees (for classification). In theory they should be good at finding rectangular regions, but imho they don't do it well for an arbitrary rectangle that is not adjacent to the edges of the original rectangle. Lots of rubbish leaves appear, for example. This is especially noticeable for rather weak patterns, which are the norm for our problems.
There is an idea to switch from trees to simple rectangle search, when splits are made not one by one, but several at a time. A quick search showed that something similar already exists - RBC (Rectangular Boundary Classifier). Then it is probably possible to do bagging and maybe even bousting on it.
Another naturally arising idea is to move from the classification task to the optimisation task. For example, when one simply searches for a rectangle that maximises profit by the sum of deals that fall into it.
There is some doubt about the decisive trees
Another naturally occurring idea is to move from the classification problem to the optimisation problem.
In fact I have about 40 of them in a box - used for sale - confiscated from the auction - need to set up somehow will be.
But I don't use them myself - I always have a computer at hand, and the rest of the time I rest from business.
Thinking my thoughts from 6 years ago, straight up cried)
)
)
Anticipating the reindeer roundabout optimisation algorithm :)
These promptus are capable of a lot).
Although I only meant that I already wrote in this thread about some algorithm related to rectangle construction. Not six years ago, of course, but long enough ago to forget all the specifics - I don't even remember what words to look for in the posts).
These promptus are capable of a lot of things).
Though I meant only that I already wrote in this thread about some algorithm related to rectangle construction. Not six years ago, of course, but long enough ago to forget all the specifics - I don't even remember what words to look for in the posts).
Yeah, I recall something like that, but I've never come across it myself. Need some benchmarks for comparison, apparently.
I haven't seen something like this in any popular libraries for time series classification.
There are some doubts about solving trees (for classification). In theory they should be good at finding rectangular regions, but imho they don't do it well for an arbitrary rectangle that is not adjacent to the edges of the original rectangle. Lots of rubbish leaves appear, for example. This is especially noticeable for rather weak patterns, which are the norm for our problems.
There is an idea to switch from trees to simple rectangle search, when splits are made not one by one, but several at a time. A quick search showed that something similar already exists - RBC (Rectangular Boundary Classifier). Then it is probably possible to do bagging and maybe even bousting on it.
Another idea that naturally arises is to switch from the classification problem to the optimisation problem. For example, when one simply searches for a rectangle that maximises profit by the sum of deals that fall into it.
If 2 chips, it will quite find a closer boundary to the actual laid rectangle. Even in increments of 1/100.
Do you have any iphones 15? I'll take one :))) For the camera. Other than that, androids are winning right now.
iPhones were stolen on rendition, and those that weren't - sold already.
Verification went through with RF. But for nothing, they won't let you enter the contest.
It is always unprofitable to buy fresh - a high markup, it is better to wait a couple of years, when prices will be better, technologies are tested and improved, and the software is adapted.
Modern laptops on x86 already have good autonomy for browser tasks, if you really need it. I don't need it.