This thesis investigates the application of machine learning models for predicting and recommend- ing student career aspirations based on academic performance and extracurricular activities. Lo- gistic Regression, Random Forest, SVM, XGBoost, and Neural Network models are employed to analyze a dataset from Kaggle, which includes academic scores, personal information, and extracurricular activities of 2000 students. The study aims to identify potential career paths for students and assist educators in providing personalized guidance. Among the models, the Random Forest Classifier demonstrated the highest performance, leading to the development of an effective career aspiration recommendation system. This system has significant implications for enhancing student career development programs by offering data-driven insights and support.