With the rapid expansion of Twitter’s user base across diverse demographics, the proliferation of fake profiles has become a pressing concern. This study addresses the need to identify and mitigate such fraudulent accounts. Our approach involves feature extraction from Twitter accounts via Twitter4j and subsequent model training employing supervised machine learning techniques. Various models are trained and evaluated to discern their effectiveness in fake profile detection. Results are meticulously analyzed to determine the most accurate model for this task. This research contributes to the development of robust methods for tackling the growing issue of fake profiles on Twitter, enhancing the platform’s security and user experience.