August 2025
Beginner
236 pages
7h 51m
English
|
12 |
Developed inside the computer science community in the 1990s, support vector machines (SVM) was initially designed for predicting numeric and categorical outcomes as a double-barrel prediction technique. Today, though, SVM is mostly used as a classification technique for predicting categorical outcomes.
As a classification technique, SVM is similar to logistic regression, in that it’s used to filter data into a binary or multiclass target variable. But, as seen in Figure 41, SVM sets a different emphasis on the location of the classification boundary line.

Figure 41: Logistic regression versus SVM
Read now
Unlock full access