This website is provided for external and public reference. Course materials and any timely course information are communicated only within Canvas.

About Emerging Topics in Computer Science Courses

CP4285 is part of the CP428x Emerging Topics in Computer Science series at NUS Computing. These are pilot courses, each run for a single semester only, with the intention of eventually becoming a permanent offering. Students should expect that the course is not yet fully mature: content, assessments, and delivery are actively evolving. The series exists to expose undergraduates to emerging areas of computer science before they become established parts of the curriculum.

Why Recommendation Systems?

Recommendation systems now shape many everyday decisions: what people read, watch, buy, study, apply for, and who or what receives attention. Their influence extends beyond convenience into visibility, opportunity, trust, and social outcomes, making it important to understand not only how these systems work, but also what values and trade-offs they encode.

About This Course

CP4285: Modern Recommendation Systems examines the algorithms, data, and design trade-offs behind contemporary recommender systems. The course connects classical recommendation methods with modern neural approaches, and emphasizes practical implementation, careful evaluation, and responsible deployment in real-world settings.

CP4285 covers classical methods, neural architectures, ranking and retrieval pipelines, sequential models, graph-based recommendation, online learning, and emerging LLM-based approaches. Ethical issues are interwoven throughout, including bias, fairness, privacy, exposure, transparency, and stakeholder impact. Students apply these ideas in a hands-on group project requiring problem formulation, dataset work, baselines, model design, evaluation, critique, and final presentation.

The course is hosted by WING.NUS, the Web IR / NLP research group at NUS led by Min.

Prerequisites: CS2109S (Introduction to AI and Machine Learning) or equivalent, and completion of at least 120 units. Students without CS2109S but with equivalent background may seek approval from Min.

Workload: (2-0-0-3-5) — 2 hours lecture, 3 hours projects and assignments, 5 hours preparatory and other work; approximately 10 hours per week.

Learning Outcomes

By the end of the course, students should be able to:

CLOOutcome
CLO 1Explain and compare classical recommendation methods, including collaborative filtering, content-based filtering, and hybrid approaches.
CLO 2Implement matrix factorization and neural recommendation models using modern deep learning frameworks.
CLO 3Design and execute rigorous offline evaluation protocols using appropriate ranking metrics.
CLO 4Analyse the cold-start problem and propose strategies to address it.
CLO 5Critique recommender systems from fairness, privacy, transparency, and stakeholder impact perspectives.
CLO 6Explain advanced recommendation architectures including sequential, graph-based, multi-objective, and LLM-enhanced systems.
CLO 7Design and justify a complete recommendation system pipeline from problem formulation through evaluation and ethical analysis.
CLO 8Communicate and defend recommendation-system designs and results to a technical audience.