Brain tumor prediction using machine learning has become an essential research area in medical image analysis due to the increasing demand for early, accurate, and automated diagnosis. Manual examination of MRI scans is time-consuming and prone to human error. This study proposes a machine learning-based system to predict and classify brain tumors from MRI data. The workflow includes image acquisition, preprocessing, feature extraction, model training, and prediction. Preprocessing techniques such as noise removal, normalization, and segmentation enhance image quality and highlight tumor regions. Extracted features train supervised learning models, enabling effective classification of normal and abnormal tissues. The proposed approach reduces dependency on manual interpretation and supports radiologists with fast, reliable results. Designed to be scalable and cost-effective, the system demonstrates the potential of artificial intelligence to improve healthcare outcomes, reduce diagnosis time, and enhance treatment planning.