Skip to content

Prediction interval for Random Forests #4768

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
pengparic01 opened this issue May 25, 2015 · 3 comments
Open

Prediction interval for Random Forests #4768

pengparic01 opened this issue May 25, 2015 · 3 comments
Labels
Enhancement Moderate Anything that requires some knowledge of conventions and best practices module:ensemble

Comments

@pengparic01
Copy link

Hi there,

Is there any plan to add prediction interval (range prediction) to the RandomForecastRegressor library? I think that will be a super useful (and necessary) addition!

Thanks,
Chen
@amueller
Copy link
Member

Not really planned. What is the usual interval you want to predict? a 95% confidence interval? It should be fairly easy to implement, but a) we don't have an API for that and b) I'm not sure how well-calibrated the estimate of the forest would be.

I'm sure @glouppe can give a more informed answer.

@pengparic01
Copy link
Author

I was thinking similar to the GBRT library, where you can specify the alpha value to get a certain quantile of the prediction range as the final estimate. @glouppe Is it possible to implement?

@glouppe glouppe changed the title Generate prediction interval? Prediction interval for Random Forests Oct 19, 2015
@glouppe glouppe added Enhancement Moderate Anything that requires some knowledge of conventions and best practices labels Oct 19, 2015
@glouppe
Copy link
Contributor

glouppe commented Oct 19, 2015

See also #3645

@lorentzenchr lorentzenchr mentioned this issue Dec 13, 2020
Open
4 tasks
@ogrisel ogrisel mentioned this issue Dec 1, 2023
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Enhancement Moderate Anything that requires some knowledge of conventions and best practices module:ensemble
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@amueller @glouppe @cmarmo @pengparic01