Recommendation Systems Education using Project-Based Learning (PBL)

Recommendation systems are a crucial component of digital platforms, enabling personalized user experiences across industries. This study explores the integration of Project-Based Learning (PBL) in teaching recommendation systems to undergraduate students, a method aimed at enhancing their understanding of this complex Artificial Intelligence (AI) application through real-world scenarios. Through PBL, students engaged in collaborative, clientfocused projects that simulated real industry challenges, promoting technical skills and problem-solving competencies essential for computing careers. The methodology combined quantitative and qualitative analyses: student performance data was tracked across multiple project sprints to evaluate skill progression, and in-depth interviews with faculty were conducted to gather insights on PBL’s efficacy in recommendation system education. The results demonstrate that PBL not only boosts technical proficiency in developing recommendation models but also reinforces teamwork and critical thinking skills, providing a framework for effective AI education in higher learning. This case study with 80 participants contributes valuable findings to the adoption of active learning methods for preparing learners for real-world AI challenges.