How to Use Approximate Leave-one-out Cross-validation to Build Better Modelsby@ryanburn
3,719 reads

How to Use Approximate Leave-one-out Cross-validation to Build Better Models

tldt arrow
Read on Terminal Reader
Read this story w/o Javascript

Too Long; Didn't Read

Leave-one-out Cross-validation (LOOCV) is one of the most accurate ways to estimate how well a model will perform on out-of-sample data. For the specialized cases of ridge regression, logistic regression, Poisson regression, and other generalized linear models, ALOOCV gives us a much more efficient estimate of out of-sample error that’s nearly as good as LOOCV. In this post, I’ll cover:What is ALOocV and how to use it to identify outliers in a training data set.

Company Mentioned

Mention Thumbnail
featured image - How to Use Approximate Leave-one-out Cross-validation to Build Better Models
Ryan Burn HackerNoon profile picture

@ryanburn

Ryan Burn

Mathematical Engineer | Building better models: buildingblock.ai


Receive Stories from @ryanburn

react to story with heart

RELATED STORIES

L O A D I N G
. . . comments & more!