Machine learning in trading: theory, models, practice and algo-trading - page 2918
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
By the year 2000, 1 terrabyte of data, 8000 tools were being collected and analysed every year. Everything that could be evaluated was analysed, news, newspaper articles... And that's in the year 2000. 140 employees.
Some sort of life hacks that allow you to algorithmise the non-algorithmisable,
to turn into code what cannot be explained, what the eye sees, the brain understands, but you can't describe it with ordinary code....
It is also possible to perform any technical analysis, for example, to build channels by regression or whatever and anything completely on automatic, and the whole code in 10 lines ))))
R is the best language in the world! :)
It is also possible to perform any technical analysis, for example, to build channels by regression or whatever and anything completely on the machine, and the whole code in 10 lines)))))
R is the best language in the world! :)
Open a private chat room on the language, I'll sign up. I think you'll find a few more followers. No chatter, no bickering. Concrete code discussion of improvement, etc.
It is also possible to perform any technical analysis, for example, to build channels by regression or whatever and anything completely on the machine, and the whole code in 10 lines)))))
R is the best language in the world! :)
Any historical data is analysable by any logic.
Try to create an image of the market one step ahead and I will be interested to communicate with you.
Any historical data is amenable to analysis by any logic.
Try to create an image of the market one step ahead and I will be interested to communicate with you.
The value of this particular craft is that it can divide a chart into pieces like a human does, and then you can do whatever you want with these pieces.
The value of this particular craft is that it can divide a graph into pieces like a human does, and then you can do whatever you want with these pieces.
You don't have the ability to split a future graph yet. You don't even understand what I'm getting at.
You don't have the ability to divide the future yet. You don't even understand what I'm getting at.
As you can see, the algorithm has divided the prices into zones/clusters/states...
coloured zones are clusters, white zones are what the algorithm considers noise....
And now the most interesting thing, what are the PD/SP levels in terms of the second picture above? These are transition zones from one cluster to another (from one state to another).
We don't see it, but we intuitively understand it, and now it's possible to algorithmise it.
And I forgot to tell you, it always works, not just in this one picture.
About two or three years ago, in this thread, I suggested breaking the history on large TFs, for example daily bars, into clusters. Then to select (cluster) characteristic clusters into groups. And then for each such group on small TFs, let's say 5M, to select, find, invent, in general, create the most optimal trading system.
Trading on new quotes will look as follows:
1. The current cluster and its belonging to the group are recognised.
2. The TS optimal for it is launched.
3. If it is diagnosed that the cluster is over, trading stops until the next cluster is identified.
About two or three years ago, I think in this thread, I.......