Spam messages are a persistent problem in modern communication, and now SMS-based scams are on the rise.Data mining techniques are applied to analyze and predict spam patterns using the SMS Spam Collection Dataset.Logistic Regression is used as the primary classification model, while K-means clustering is employed to identify underlying structures in the data.The study reveals class imbalance in the dataset, with spam messages being fewer in number, and identifies common keywords in spam and ham messages.