- There are arguments like, “logistic regression is regression,” or “No, it’s not regression, it’s classification.”
- It is similar to the discussion of “Are Python and Ruby variables passed by value or by reference to a function? - An example of choosing the wrong two options. In this case, the reference is passed by value.
- Logistic regression solves classification problems by finding probability values in regression.
- Re-posted from a previous article in [Regression and Classification
-
Misleading point: “logistic regression” is overwhelmingly used for classification problems, not regression problems
-
Logistic regression is a method of solving the classification problem of “which group one belongs to” by finding the real value of “probability of belonging to a group” through regression. In other words, it is equivalent to converting a classification problem into a regression problem and then solving it.
-
Machine Learning
This page is auto-translated from /nishio/ロジスティック回帰は回帰か分類か using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.