Find robust parametric combinations: K-Means

Hi,


I would like to suggest the inclusion of a data mining algorithm called K-Means. The K-Means algorithm is used to make similar groupings in a data set.


From what I have seen optimization already uses genetic algorithms when we have many parameters. The problem then comes in choosing a robust parameter set (having "good neighbors") for a target ratio. Currently we use the 3D map 2 to 2, but if we have many parameters it becomes slow and complicated.


Ideally, search for robust parametric combinations should be added using the K-means Clustering algorithm. And not just one, but several depending on the objective ratios.


For example, software similar to yours already has it implemented:
https://alphadvisor.com/en/user-manual/optimizer-module/


Other references:
https://www.quantnews.com/k-means-clustering-creating-simple-trading-rule-smoother-returns/
https://link.springer.com/chapter/10.1007/978-3-540-72821-4_7
https://medium.com/datadriveninvestor/stock-market-clustering-with-k-means-clustering-in-python-4bf6bd5bd685


I hope you take it into account, it could be a quality leap.


Regards,

Attachments
No attachments
  • Votes +3
  • Project StrategyQuant X
  • Type Feature
  • Status Archived
  • Priority Normal
  • Assignee None

History

m
#1

Mariano

14.04.2020 22:29

Task created

m
#2

Mariano

14.04.2020 22:29
Voted for this task.
Rr
#3

Partizanas

15.04.2020 01:08
Voted for this task.
BS
#4

BobS

15.04.2020 06:26
Voted for this task.
MF
#5

Mark Fric

10.03.2021 12:48

Status changed from New to Archived


Votes: +3

Drop files to upload

or

choose files

Max size: 5MB

Not allowed: exe, msi, application, reg, php, js, htaccess, htpasswd, gitignore

...
Wait please