Machine learning in trading: theory, models, practice and algo-trading - page 3035
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
A straight line corresponds to perfect uniformity. The difference from a straight line is non-uniformity. I want to minimise the irregularity.
What's wrong with standard deviation?
OK, you can do that - the result is the same in interpretation
Here we go.)
The irregularity is 30% greater, and the angle is only 3 degrees different. I don't think 3 degrees is enough.
If we move the first point from 0 to -1.22, I think we'll have an exact hit.
But we need to leave it at 0, and leave the maximum in the same place. And move the other points and achieve coincidence of lines.
In my opinion, the sum of moduli of deviations will better describe the deterioration of the balance line. In this case, it's 30% and it will deteriorate.
I'm not in favour of randomly mixing all the strings - that's just the way to use standard metrics, with no consideration of balance.
The importance of order in the sample means that there are dependencies between the rows in the data table. Dependencies are always a bad thing, and are usually carefully avoided.
What's wrong with standard deviation?
I thought - it doesn't correspond.
Here we go.)
The irregularity is 30% more, and the angle is only 3 degrees different. I don't think 3 degrees is enough.
I don't know by how much, I can't see it by eye. Unevenness in percentages - that seems like a strange approach to me - but okay.
If you move the first point from 0 to -1.22, I think you'll have an exact hit.
But we need to leave it at 0, and leave the maximum in the same place. And move the other points and achieve a coincidence of lines.
In my opinion, the sum of moduli of deviations will better describe the deterioration of the balance line. In this case, it's 30% and it will deteriorate.
It will match, but not the angle. I just do not understand your logic - to move this and that, then the structure will change - it will not be comparable at all.
Here you have moved zero and maximum - all the same. It is not important how much it has improved, but the fact of improvement. It is a relative indicator for choosing among many other options.
Inventing their own Sharpe and Sortino) With blackjack and other necessary stuff)
Now, if only they would do it somewhere else.... But, such dreams.... And this is just rubbish in the thread.
I don't know by how much, I can't see it by eye. I don't know how much - I can't see it by eye.
I still need to think/experiment whether to measure in % or in abs units. I think abs. is better.
Here's if they'd do it somewhere else.... But that's just a dream.... This is just rubbish in the thread.
Dreams from you to hear at least some new useful information, which can be applied in a useful way.
I still need to think/experiment in % or abs units. I think abs. is better.
You can send me the balances - I will evaluate them with my method - tell me how it turned out.
You can send me the balances - I will evaluate them with my method - tell me how it turned out.
Next week I'll do what I have in mind.