Machine Learning-Based Enrollment Prediction for a Higher Education Institution

Abstract  – This research focuses on the BS Information Technology (BSIT) program at Lyceum of the Philippines University-Batangas, aiming to develop and assess a machine learning-based enrollment prediction model. The study begins by analyzing the demographic composition of enrolled individuals, revealing a dynamic student body with a notable gender imbalance. While enrollment rates remain high, the gender disparity prompts a deeper investigation for targeted recruitment strategies, fostering inclusivity within the BSIT environment.
Prospective students express the significance of program offerings and financial aid, with personal recommendations, online presence, and social media engagement emerging as crucial influencers. Recommendations emphasize prioritizing authentic word-of-mouth promotion, optimizing online visibility, and leveraging social media for effective recruitment in a competitive landscape.
The research delves into student data on enrollment, goals, and satisfaction, highlighting areas for improvement in addressing neutral responses and catering to diverse information sources, decision timelines, and post-enrollment aspirations. Recognizing this diversity, the study recommends multifaceted communication, tailored support, and flexible pathways to enhance the overall educational experience.
Utilizing machine learning in Google Colab, the study predicts enrollment trends up to SY 2028-2029. Strategic recruitment, adaptation to student demands, targeted marketing, and financial aid are proposed to reverse second-year enrollment dips. The positive trajectory in subsequent years signifies successful student engagement and program offerings, emphasizing the need for continuous adaptation to ensure student success.
The recommendations derived from the study advocate leveraging machine learning for trend forecasting, monitoring strategy effectiveness, strategic marketing, creating a welcoming learning environment, and adapting recruitment strategies to demographic shifts. Additionally, the study emphasizes the importance of fostering a supportive academic community and implementing proactive measures to enhance student success.

 Keywords – Enrollment Prediction, Machine Learning, Recruitment Strategies, Student Demographics, Student Satisfaction

https://doi.org/10.70979/KFTM3818