Linear Models
Models that use linear combinations of features to make predictions
Linear models are fundamental algorithms that model relationships between input features and target variables using linear combinations. They assume the relationship can be represented as a weighted sum of the input features.
Linear Regression
Linear regression predicts continuous numerical values by fitting a line (or hyperplane) through the data. It's one of the most interpretable models, where each coefficient shows the direct impact of a feature on the target.
For a comprehensive guide on linear regression, including assumptions, optimization methods (OLS, gradient descent, SVD), evaluation metrics, and practical tips, see Linear Regression.
Logistic Regression
Despite its name, logistic regression is a classification algorithm. It applies the sigmoid function to a linear combination of features, transforming outputs into probabilities between 0 and 1. This makes it ideal for binary classification tasks like spam detection or fraud identification.
For a comprehensive guide on logistic regression, including the sigmoid function, log-odds, Maximum Likelihood Estimation, regularization, and handling imbalanced data, see Logistic Regression.