Students’ employability, especially in professional studies, continues to be a serious issue for educational institutions. One of the significant challenges is the early identification of employability, which can help create a better relationship between students’ skill sets and the varying requirements of establishments. Better prediction of employability assists students in matching their competencies to industry requirements, thus closing the gap in skills and enhancing the campus placement ratio. Machine learning has become an effective tool for analyzing student data, forecasting employability patterns, and providing proper recommendations for further processes. Using machine learning techniques, the institutions can measure student performance, determine major employability drivers, and suggest custom skill development techniques. This provides graduates with optimum preparation for employment, improving career opportunities, and compatibility with employer specifications. In the past decade, machine learning techniques have come a long way in enhancing employability predictions to be more accurate and dynamic. This paper systematically reviews machine learning techniques and their applications in predicting student employability with campus placement probabilities from 2010 to 2024. Through a thorough literature review and classification of research articles, the researchers identify significant trends, challenges, and future research directions in campus recruitment. Educational institutions can leverage these developments to implement data-driven approaches to improve student employability, campus placement outcomes, and industry-academia collaboration.