Classification models play a crucial role in predictive analytics by assigning observations to distinct categories based on predictor characteristics. This chapter discusses two widely used classification techniques: logistic regression and support vector machines (SVM). Logistic regression, a classical statistical model, is valued for its interpretability, while SVM provides a more flexible approach by accommodating nonlinear decision boundaries. The chapter explores the theoretical foundations of both methods and demonstrates their application in classifying bank loan customers to identify potential borrowers. Model performance is assessed using accuracy measures and visualization tools to aid in model selection. Additionally, practical implementation in R and Python is provided, offering step-by-step guidance for applying these techniques in real-world loan classification tasks.