Special Topics: Recommender Systems

MSDS 490-DL Special Topics: Recommender Systems

This course will equip students with knowledge and hands-on experience in designing, implementing, and evaluating recommender systems. Through a blend of theoretical foundations and practical applications, students will explore data preprocessing, matrix factorization, embedding-based models, sequential recommendation models, and deep learning techniques. Leveraging industry-standard frameworks, such as, PyTorch, the course emphasizes scalability, explainability, and ethical considerations in real-world scenarios. Engaging weekly assignments, complemented by current research will foster deep learning and peer discussions, preparing students to tackle complex challenges in the field of recommender systems. This course is ideal for those seeking to master advanced techniques and apply them to impactful, large-scale applications. Recommended prior courses: MSDS 410-DL Supervised Learning Methods and MSDS 411-DL Unsupervised Learning Methods. Prerequisites: (1) MSDS 420-DL Database Systems or CIS 417 Database Systems Design and Implementation and (2) MSDS 422-DL Practical Machine Learning or CIS 435 Practical Data Science Using Machine Learning.

One of the few courses in the MSDS program that uses PyTorch for deep learning.

Go to the main page for Data Engineering.