'Logistic regression' is:

Logistic Regression uses the sigmoid function to map any real-valued input to a probability between 0 and 1 using P(Y=1) = 1/(1 + e^(-z)). A threshold (typically 0.5) converts probabilities to class predictions. Output is interpretable as log-odds (coefficients) show feature importance and direction. It assumes linear relationship between features and log-odds. Logistic regression is used in banking for Binary credit decisions (approve/reject), fraud detection (fraud/not fraud) and churn prediction (leave/stay). It can be extended to multi-class via softmax (multinomial logistic regression). Despite its name, it is a classification, not a regression, algorithm.