A retail company wants to optimize its marketing strategy by segmenting customers based on purchasing patterns. Which technique is most suitable for this task?

Explanation: K-means clustering is a powerful unsupervised learning algorithm for grouping customers into distinct segments based on similar purchasing behaviors. It minimizes intra-cluster variance and ensures that customers in the same cluster exhibit closely related characteristics, such as spending frequency, product preferences, or average order value. Retailers can use these clusters to personalize marketing campaigns, recommend products, and allocate resources effectively. For instance, a cluster with high-spending customers might be targeted with premium offers, while infrequent buyers might receive discounts. K-means is computationally efficient and provides actionable insights for customer segmentation. Option A: Regression analysis predicts outcomes but does not group customers into distinct segments. Option C: PCA reduces dimensionality and aids visualization but is not inherently a segmentation technique. Option D: Sentiment analysis evaluates customer opinions but is unrelated to purchasing behavior segmentation. Option E: Time series analysis identifies trends over time but does not classify customers into groups.