This paper presents a decision tree model designed to predict student academic performance, based on multiple factors including demographic data, study behaviors, and extracurricular activities. With the rise in student diversity and the expansion of digital learning, the institutes need effective ways to assess and support students. The proposed model classifies students into different performance categories, helping educators find influential factors on academic outcomes. When weighed to different models like KNN, SVM, and logistic regression, decision tree model provides higher precision and recall by efficiently handling missing data. The model’s simplicity, ability to work for various data types, and reduced processing time make it practical choice for real time predictions. Future enhancements may extend this approach to support personalized study recommendation, further enhancing the academic support across diverse learning environments.