Knowledge Maxxing← Back to topic library
ML MaxxingIntermediate75 sec
Logistic regression
Logistic regression predicts the probability of a binary outcome by passing a weighted sum of features through a function that squashes the result between 0 and 1.
Prerequisite: Linear regression
What matters
Despite its name, it is a classification method, not a regression one; the squashing function is what turns an unbounded weighted sum into a valid probability.
Example
A logistic regression model might output 0.82 for 'probability this customer churns', which is then compared against a threshold to make a final yes/no prediction.
Common misconception
Logistic regression is not used for predicting continuous numeric values; despite the word 'regression', it is specifically a classification technique.
Recall question
Why is logistic regression a classification method despite its name?
Keywords and related concepts
logistic regressionsigmoidbinary classificationlinear regression