Estimating the prevalence of rare events — theory and practice
The Unofficial Google Data Science Blog
AUGUST 27, 2019
There are many strategies we can use to estimate this quantity, and we will discuss each option in detail. When training a classifier with few positives in the population, one common strategy is to over sample items with positive labels, and/or down sample items with negative labels. This is straightforward and easy to implement.
Let's personalize your content