Student performance vaticination plays a pivotal part in relating and addressing academic challenges early [3], enabling targeted interventions and personalized support. This study aims to improve academic outcomes by accurately predicting student performance. To achieve this thing, varied machine learning algorithms were employed to develop dependable models [2] based on student-related attributes such as demographic information, socio-economic background, past academic records, and engagement factors. The models were trained on a portion of the data set and evaluated using appropriate metrics to measure predictive accuracy. The results demonstrate that the machine learning algorithms were effective in predicting student performance [5], with varying levels of accuracy. This information enables educators to identify and support students who may require additional resources. By employing machine learning algorithms, educational stakeholders can make informed decisions and allocate resources effectively to improve student outcomes.