Numerical series density - page 9
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
ok, where are the deltas for number 10
Third column.
and then the delta between 13 and 15 is zero?
Here, to make it clearer - does that make more sense? By the intersection of the column and the row you will find the delta. By the way, you are right - there is an error in the formula, apparently - we'll figure it out later.
Then the bottom line changes as well
Mine is Algorithm 1 so. Now, we have density points, that is, the numbers that are closest to the other numbers on average
Density centres, so to speak, in ascending order
Now, if you want to find clusters, as you said, i.e.
these are groups of numbers close together do I understand correctly?
for the initial cluster what do you take as how many numbers should be close 2 or 3? and at what max distance?
Mine is Algorithm 1 so. Now, we have density points, that is, the numbers that are closest to the other numbers on average
Density centres, so to speak, in ascending order
Apparently so.
Now, if you want to find clusters, as you said.
they're groups of numbers close together, am I right?
for the initial cluster that you take as how many numbers should be close 2 or 3? And at what max distance?
We don't know it - there is no criterion. On the contrary, we need to determine the density of the grouped numbers (maybe in all variants) and then select those numbers which will have the maximum density.
But, I don't mind seeing your thinking - let's say the minimum in a group should be 4 numbers - distance not known - density max... As a density take the delta between the first and last number in the group, divided by the number of digits in this group (you can propose your own method) (the smaller the coefficient will be, the better).