Machine learning in trading: theory, models, practice and algo-trading - page 1754
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
Let's better go to the classification, it is clear with the metrics, you can always compare with someone, and it's simple.
I have an interesting idea, such a kind of useful chlege
What if we create a dataset (one for all) with target and prices + various useful indicators and post it here, make a test and a trace, and then "test2" for full OOS check of the already trained model.
People will upload dataset and try to improve the quality of classification, if something works, it will be added to the dataset as a chip/indicator.
The result:
1) dataset gets better, the chips in it get better.
2) Models are improved
3) Understanding of how to work with features and AMO evolves.
4) Even though it is remote, it is a team work
5) Benefits for all, everyone will finally have a community, not a quarrel, and Challenge is an incentive to do better than anyone else.
each to his own...
each about their own...
A single dataset with a single target for all
This is exactly the solution!
Then there will be more communication between everyone because everyone is in one project, not each in his or her own.
a single dataset with a single target for all
This is exactly the solution!
In this case, the conversation will not be about each other, but all for the improvement of the single, and there will be more understanding among all, since all are in one project, not each in his own.
Socialism is good, but when the crowd lacks common understanding, common faith will not save us.
EACH of us must believe in what he/she believes, for it will be rewarded according to your faith and deeds.
socialism is good, but when the crowd has no common understanding, a common faith will not save
EVERYONE must believe in something of their own, for it will be rewarded according to your faith and your deeds.
are you drunk? ))
will be the same, but from left to right.
Ugh, and I didn't realize that the right track. Then it's not interesting, in the past you can't haggle (in the future you can't optimize)...
Ugh, and I did not realize that the right track. Then it's not interesting, you can't haggle in the past (you can't optimize in the future)...
You have a biased attitude to the position of the test pieces. Much more important is the preservation of the characteristics of the TC on the OOS
The OOS from the front has a certain sense in the TS with the analysis of the long-term trend, depending on time. Otherwise, there is no difference.You have a preconceived notion about the position of the test pieces. Much more important is the preservation of the characteristics of the TC on the CB
OOS from the front has a certain sense in the TS with the analysis of the long-term time-dependent trend. Otherwise there is no difference.Well, it's not on a level playing field.
You can speak to me by name.
Well, it's not on a level playing field.
It's okay to speak to me on a first name basis.
about you - all of you here)
In general, it's a flawed approach, you can accidentally fit any piece - whether in front or behind
Well, it's not on a level playing field.
You can address me as you.
If you take the height of triangles as a probability of preserving the found regularity, then Maxim's approach is more logical.
about you - all of you here)
in general, this is a flawed approach, you can accidentally fit any piece - at least the front or back
What do you look at the local trends, they are different in time, how do you gradate, at least the logic of how? All of course so. The answer is in the test on all symbols from 70 to 20 year tickwise )))) and if the profit in 90% of the row ))))) Although damn probability is a no brainer... and 10% is always .... You should always train and opt out too....