Machine learning in trading: theory, models, practice and algo-trading - page 498
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
I have one :)
With respect.
P.S. it's not so important whether he can or can't, it's the result of the prediction that counts. You can make predictions with a hammer, but if the result deserves attention, it should be taken into account.
there are still some errors in my opinion with the model errors, the smaller the set is always less error, I do not understand rpikol
create your error calculation.
If it is like you said, most likely there is an equation to a certain number, for example if you have a 1000 300 errors counts 300/1000 if you input 100 and output 30 errors it can calculate based on the number of errors, for example 30/1000.
you can check whether the dependence is linear or not by inputting only 3 samples different in number.
Regards.
make your own error calculation.
if you do it like you said, most likely it will equate to a certain number, for example if you have 300 for 1000 it will calculate 300/1000 if you have 100 for input and 30 for output it may calculate from the number of errors you have for example 30/1000.
Respectfully.
Yes, I guess I'll figure it out. I just do it in spurts. I did it the day before yesterday, and two days later I sat down and forgot what I'd done.)
i'm combining forests with fuzzy logic, you can do some funny things there, but they are hard to understand
Yes, I guess I'll figure it out. I just do it in spurts. I did it the day before yesterday, and two days later I sat down and forgot what I'd done.)
i'm combining forests with fuzzy logic, i can do some funny things there, but they are barely comprehensible
Sincerely.
They don't understand, like 80% of those who are here, how the code, compiler and machine works, but nevertheless it doesn't prevent them from writing EAs and selling them on the Market.
Sincerely.
Yes, the market is bullshit... investors are big ;) but you always need results there
Yes, the market is bullshit... investors are big ;) but you always need results there
The answer will be obvious, the product itself needs tuning from the creator... Otherwise it is not of great importance to the investor.
With respect.
Question for a puzzle, how can an investor get a result on this or that product if he does not know the importance of parameters and the sequence of their optimization?
The answer is obvious, the product itself needs tuning from the creator... Otherwise it is not of great importance to the investor.
With respect.
No, the investor just invests, he does not need to know the rest. The result is your work.
I don't think it's just a question of the market, but I'm sure it will be a very profitable one, as I'm sure it will be a very profitable one.
My respect.
On the market you can make simplified versions, up to a certain degree of complexity... otherwise, no matter how you describe everything in detail - will flood you with questions, a lot of newcomers... as a result you become a manager-consultant, not a developer
On the market you can make simplified versions, up to a certain degree of complexity... otherwise, no matter how you describe everything in detail - they will flood you with questions, a lot of newcomers... as a result you turn into a consulting manager, not a developer
I have come to the conclusion that Expert Advisors must work in accounts and yield profits.
I think that the main thing is to make them work on my own, in my opinion, they should work on accounts and bring profit if they want to help me.
I have come to the conclusion that Expert Advisors must work in the accounts and yield profits.
And in my opinion nobody needs all these codes) except for some service functions.
I've exchanged ideas - in the end we usually come to the conclusion that no one understands what's done in the other, and everyone is like this: oh no... next time...