In today’s very competitive educational world, the future of students has now become a priority in the minds of educators, parents, and students. It’s a challenge to identify the best-suited areas of study that congregate about an individual’s strengths and inclinations. The development of personalized learning has become a critical determinant of academic outcomes and career advancement for students, but the current wealth of career options and personal responsibility for sorting through the options without personal guidance leaves a gaping hole in making informed choices. This, in turn, underscores the critical demand for an effective, data-driven recommender system that directs students to the courses that they are the readiest to benefit from. The basis for a personalized course recommender system is developed through this research which outlines the need for an optimized student classification model that can distinguish between fast and slow learners. The model achieves this via leverage of a dataset comprising both professional and personal attributes from birth, like academic performance, family background, age, gender, classroom engagement, and attendance, to provide the reader with very precise and highly relevant course recommendations. To improve the overall performance of the classification model, the Boruta feature selection algorithm was used to identify the most important features from the dataset. By focusing on the attributes that most effectively contribute to the classification problem, this approach is expected to outperform state-of-the-art methods, resulting in improved prediction accuracy. The result of this research is the intention to aid students in choosing to attend courses that resonate with their level of speed in the learning process without misleading the chance to achieve academic and career success.