In our paper, we investigate the usage of smartphone among student academic performance using a machine learning approach. Data was collected through a survey focusing on various aspects of smartphone usage patterns, including frequency, purpose, and perceived effects on learning. The dataset was preprocessed and used to train several classification models, to predict student academic performance based on smartphone usage features. The performance of the models was assessed using evaluation metrics including accuracy, confusion matrix, and classification reports. The results indicate that smartphone usage patterns are significantly correlated with academic performance. The Logistic Regression model achieved the highest accuracy, suggesting its potential for predicting student academic outcomes based on their smartphone usage behaviors. This research offers valuable insights into the intricate link between smartphone usage and academic achievement, emphasizing the potential of machine learning in uncovering key factors that affect student learning outcomes.