Logistic regression is the most traditional classification algorithm and preserves many of the advantages in interpretation as linear regression for a continuous outcome. Many algorithms such as Regression, Decision Tree-based methods, and Neural Networks are suitable for both regression and classification and involve only minor tweaks depending on the target context. However, other algorithms only really make sense in the context of classification, and a brief summary is provided for some common such classification-specific algorithms.
- Naive Bayes
- Support Vector Machine (SVM)
- Discriminant Analysis (LDA/QDA)