AI Engineering Degree Practice Exam 2025 - Free AI Engineering Practice Questions and Study Guide

Logistic Regression is a statistical method used for binary classification problems, where the outcome variable is categorical and typically involves two classes. In the context of predicting customer churn based on purchase history, Logistic Regression is utilized to analyze the relationship between various features, such as purchase frequency, customer demographics, and other relevant factors, and the likelihood of a customer leaving or staying with a service. The model outputs probabilities for the classes, allowing businesses to make informed decisions regarding customer retention strategies.

The other options do not align with Logistic Regression applications. Detecting outliers typically involves methods such as Z-scores or IQR, which are not classification tasks. Calculating the mean relates to summarizing a continuous variable and does not involve classification or prediction. Generating synthetic data for model training is commonly done through techniques like SMOTE or GANs, rather than using Logistic Regression, which is not designed for data generation.