Logistic Regression
A simple, interpretable model for binary classification — outputs a probability via the logistic (sigmoid) function.
Logistic regression is a linear model for classification: it computes a weighted sum of the features and passes it through the logistic (sigmoid) function to output a probability between 0 and 1. Despite the name, it classifies — and it remains a strong, interpretable baseline.
Worked example: to predict churn, logistic regression learns a weight per feature (higher tenure lowers churn odds, more support tickets raise it) and outputs each customer’s churn probability, with weights you can read as “each ticket multiplies the odds by X.” Gotcha: it only draws a linear decision boundary, so it underfits genuinely nonlinear problems unless you engineer interaction or nonlinear features — but its speed, calibration, and interpretability make it the right first model, and the baseline any fancier model must beat.