Advanced Recommender Systems

EIT Digital & Politecnico di Milano

In this comprehensive course, you will delve into the realm of advanced recommender systems, harnessing the power of machine learning to construct more sophisticated recommendation models. Through a series of engaging modules, you will master the integration of diverse filtering techniques, hybrid information management, and the incorporation of side information for context-aware recommendations.

  • Learn to utilize advanced machine-learning techniques for developing sophisticated recommender systems.
  • Explore the combination of various filtering approaches to enhance the quality of recommendations.
  • Discover how to integrate different forms of side information into recommender systems for more context-aware recommendations.

By the end of this course, you will possess the skills to design and implement cutting-edge recommender systems capable of solving complex cross-domain recommendation challenges, leveraging your creativity and innovation skills to drive impactful outcomes.

Certificate Available ✔

Get Started / More Info
Advanced Recommender Systems
Course Modules

The course comprises modules on advanced collaborative filtering, singular value decomposition techniques, hybrid and context-aware recommender systems, factorization machines, and the Recsys Challenge (Honors), offering a comprehensive exploration of advanced recommender system development.


This module provides an overview of advanced collaborative filtering, delving into item-based collaborative filtering as an optimization problem and exploring SLIM, Bayesian Probabilistic Ranking, and more. The module concludes with a comprehensive course syllabus, acknowledgments, and a graded assessment.


Explore singular value decomposition (SVD) techniques in this module, covering matrix factorization, Funk SVD, SVD++, Asymmetric SVD, and Pure SVD. Additionally, the module delves into explaining the model and explores recommendation items and explainability in machine learning, followed by a graded assessment.


This module focuses on hybrid and context-aware recommender systems, covering linear and list combinations, pipelining, merging models, collaborative filtering with side information, and context-aware recommender systems. It concludes with a graded assessment covering tensor-based factorization, preferences in context, and a matter of weights.


Delve into factorization machines in this module, exploring the core concepts, extending the model, and solving imbalance problems. The module concludes with a graded assessment covering factorization machines and multimedia contents.

Recsys Challenge (Honors)

This honors module presents the Recsys Challenge, offering an opportunity to apply the knowledge and skills gained throughout the course to real-world challenges in recommender system development.

More Machine Learning Courses

Applied Data Science


Applied Data Science is a 4-course Specialization by IBM, providing hands-on skills in Python, data analysis, and visualization for making data-driven business decisions....

Explaining machine learning models

Coursera Project Network

Exploring machine learning models

Machine Learning Models in Science


Machine Learning Models in Science provides a comprehensive overview of applying machine learning techniques to scientific problems, focusing on data preprocessing,...

TensorFlow for AI: Neural Network Representation

Coursera Project Network

This guided project course provides hands-on experience in creating and training convolutional neural networks with TensorFlow for real-world image analysis tasks....