College dropout remains a significant challenge in higher education, with student attendance closely linked to academic outcomes. This chapter draws on institutional data from math and computer science courses to explore the relationship between class attendance and final grades. Using both traditional statistical regression and k-means, a machine learning technique, we identify patterns—such as prolonged absence streaks and declining attendance later in the semester—that can serve as early warning signals. These findings show how attendance data can inform timely, equity-focused interventions. To make this work accessible to a broad audience, the chapter includes two methods sections: one written in plain language for non-technical readers, and another following conventional academic standards. This structure is designed to help readers without a background in data science begin to engage confidently with machine learning research. The chapter concludes with recommendations for institutions, such as supportive outreach, simplified digital tools, and thoughtful use of attendance data to improve student persistence, while remaining mindful of ethical and privacy concerns.