Schizophrenia refers to severe brain disease that influences the way an individual thinks, feels, and acts. It affects approximately 1 in 100 individuals globally and is challenging to diagnose in the early stages due to the fact that its symptoms are varied. In this research, we employed a dataset of 470 brain activity images (Electroencephalogram scans) to train a machine learning model to identify schizophrenia. We divided data into the three sets: 70% for training, 20% for validation, and 10% for testing. Various machine learning methods, including K Nearest Neighbors, Random Forest, and Logistic Regression, were experimented with. The best performance was from an ensemble of Logistic Regression and Random Forest methods, with an accuracy of 97.87%. This study indicates that machine learning can prove to be quite helpful in early detection of schizophrenia, which could assist physicians in treating patients in a better manner.