Machine learning in trading: theory, models, practice and algo-trading - page 2432
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
6 trades
I added about baskaks to make it clearer
Baskak- the representativeof the Mongolkhan in the conquered lands, the collector of taxes(bailiff [1]).
You don't even have that, chew your fat:)
A monkey is a better trader ))))) I would be ashamed to show it
Those who do not even know what NMR is, you can safely send to the PS for permanent residence, or read from the first page of the whole topic, squeamishly flipping through the verbal urges of Rena and the flying baskaks. Because they will never understand the philosophy of the topic :)
Do you know what a PLM is?
Do you know what PLM is?
You also suggest that they play poker on Carnot cards ))))
it does not work, at least to write on the forum about the quality of products in the Market is meaningless
as admin says, forum attendance by buyers tends to zero, they are only marked on the main page
You also suggest that they play poker on Carnot cards ))))
)))
I prefer Preferance)
Implemented the algorithm on the principles of "knowledge base" version 1.0.0 :)
Differences from "classics" of classification...
1) Algorithm is not trained on class labels, it has no labels at all, but there is "memory" (knowledge base).
2) There is a strong suspicion that there is no retraining in principle...
3) The algorithm does not predict the next moment in time (it does not predict the current trend), but predicts market reversal zones.
4) There were no classifiers and regressors used, but only data reduction (dimension reduction) and clustering
The picture shows the zones of supports and resistances drawn by the algorithm, the dim color is pp/sp with low probability of + - 50%
The bright color shows the zones in which the algorithm is 75% confidence and above.
The moment the zone appears on the chart is marked with a dot on the chart, or the beginning of the zone itself...
Algorithm has not seen new data for more than 2 months, those are making decisions based on fairly outdated data, but to me pretty adequate ...
Here is today's EUR 5 min chart
I've been working on this for a long time now and I don't know how to do it, but I'm getting rid of it.
I'm planning to make a really strong robot on a powerful "knowledge base", but it's hard, I'm thinking about its implementation, my guess is that such a robot can weigh dozens of gigabytes, but it should trade well...
That's all for now...
But it should trade well...
That's all for now...
Why have you painted over the chart so much that even if you are the author, you can't see anything?
at least draw entry/exit arrows for the trading system, ideally it is tested with a tester
At a minimum, the coup trade system (buy signal ends with a sell signal and vice versa) will not work,
but maybe small takeoffs will work, although why is it better than ordinary indicators, the drawdown is better to keep silent, because this is not the main thing? ))))
ZS: if you "turn" the arrows, I think nothing will change ;)
Why have you painted over the graph so much that even as the author you do not see anything?
Those who do not even know what NMR is, you can safely send to the PS for permanent residence, or read from the first page of the whole topic, squeamishly flipping through the verbal urges of Rena and the flying baskaks. Because they will never catch up with the philosophy of the topic :)
you're already on page 10 of this mind-blowing neuron plummer
do something about it