Testing real-time forecasting systems - page 66
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
Exactly! Can you build a model by points?
A pseudo-attractor can be constructed using Tuckens' theorem
It's just that you said you would try it on a different instrument.
This will increase the prognosis tenfold :)
Found a fourth cluster with an entropy of 152.3/ No more, I think.
Let's see what happens....
As a comparison, the prediction of the baseline system. All the same, including 33 trajectories, which formed the following "clusters", in order of increasing probability of realisation:
Cluster one, combines two very close groups with entropies of 5.5 and 6.2 (9 trajectories):
Cluster two, combines two close groups with entropies of 12.8 and 13.1 (8 trajectories)
Cluster three, entropy 14.1 (7 trajectories)
Clusterfour, entropy 16.9 (10 trajectories)
The picture today is as follows:
Buy at market opening, take at 5749, stop at 5616.
The market opened with a gap to the forecast:
The picture today is as follows:
Buy at market opening, take - at 5749, stop at 5616 area.
Gap exactly on the take. )))
The position closed on the take:
The probability picture is changing a bit. Maybe the 1.5 level will sort of break through and go a bit higher (first and second cluster). OK, I'll get to the lab and check it out.