ANALYTICS IN HIGHER EDUCATION: USING MACHINE LEARNING TO IMPROVE STUDENT RETENTION AND GRADUATION RATES
VAISHALI MADHUKARRAO BODADE
Dr. AKANSHA TYAGI
Dr. UMESHWARI PRATAPRAO PATIL
DEPARTMENT OF COMPUTER SCIENCE
SHRI JAGDISH PRASAD JHABARMAL TIBREWALA UNIVERSITY, VIDYANAGARI, JHUNJHUNU, RAJASTHAN
Abstract :
This paper explores the application of machine learning in higher education to enhance student retention and graduation rates. By analyzing diverse data sources—such as academic performance, demographic information, engagement metrics, and socioeconomic factors—ML algorithms can predict at-risk students, enabling early interventions. Techniques like decision trees, neural networks, and clustering can help institutions personalize support services, optimize academic advising, and tailor retention strategies. The paper also discusses challenges, including data privacy concerns and algorithmic bias, and highlights future opportunities for integrating ML-driven analytics into institutional decision-making. Ultimately, machine learning has the potential to transform student success strategies, fostering higher retention and graduation rates across diverse student populations.
Keywords: analytics, higher education, machine learning, improve student, retention.
