Machine learning in trading: theory, models, practice and algo-trading - page 2704
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
The issue of partners in the topic of markets is complicated. Everyone wants to get more for themselves than they give to their partners. They rely on ready-made goods from their partners and run away at the first opportunity when they get what they need.
No trust - no common activity.
So, Aleksey, you have a difficult task).
It is necessary to start with the same understanding of terms and goals in setting tasks. At this stage of communication try not to get syncrosia, i.e. allergy to the interlocutor, and only if this stage is passed without syncrosia can we hope for results.
Zy. it is a difficult task to assemble a team of people you know, and it is even more difficult to assemble a team of people you don't know))).
Well yes, well yes, perhaps a dictionary of terms should be given, especially to me, as I often invent them myself....
A team works when the goals are the same and there is a profit (not necessarily in monetary units) from participation.
And the goal is to automate the search for predictors.
The issue of affiliates in the topic of markets is complicated. Everyone wants to get more for themselves than they give to their partners. They rely on ready-made products from their partners and run away at the first opportunity when they get what they need.
No trust - no common activity.
So, Aleksey, you have a difficult task).
Well, in general, it is normal to receive more than to give, peculiar to humans.
If a group of 11 people, and each will give only 10% of unique investments, then each will get 100% in exchange for their 10%, kind of profitable.
But the point is different, I think everyone thinks he is a genius or has a heightened paranoia, in other words, he thinks his knowledge is unique and super valuable and can make him happy. To pick at a task without success is to have increased viscosity, obsessiveness, and often schizoid personality traits, which is usually introversion. In general, personalities by nature are not inclined to trust others. In one way or another I have this, otherwise I would have given up.
An example of creating informative training markup for a dataset of any attributes:
Do I understand correctly that a random markup is made, then a predictor that can best describe the rndom is searched for, and then this predictor is used to re-markup and select other predictors for training?
Do I understand correctly that a randomisation is done, then the predictor that can best describe the rndom is searched for, and then the predictor is re-marked and the other predictors are selected for training?
No, all the signs and the chart at once.
Every bar in a row is marked, even in different TFs? I just don't understand how to use it in real life - how to reproduce the random that it is time to get a signal from the model.
Each bar is marked in a row, even if of different TFs? I just don't understand how to use it in real life - how to reproduce the random that it's time to get a signal from the model.
You mark it up however you want, but at the same time the graph and the features
And how do you do it - I don't understand it, how do you reproduce the target random.
As for the rest of the actions, well, if everything is good, it should work, but in fact it is difficult to achieve. I have already written earlier that I do quantisation, and for each quantum an evaluation metric - in this way I select raw predictors, let's say on the basis of an indicator.
How do you do - I don't understand it, how do you do it, how do you target random reproduction.
As for other actions, well, if everything is good, it should work, but in fact it is difficult to achieve. I have already written earlier that I do quantisation, and for each quantum an evaluation metric - in this way I select raw predictors, let's say on the basis of an indicator.
There is objective before and after evaluation. There is random markup in the articles
And I didn't get the reproduction from the articles.