Recommender systems have become indispensable for several Web sites, such as Amazon, Netflix and Google News, helping users navigate through the abundance of items. In general, recommender systems facilitate the selection of items by users by issuing recommendations for items they might like. Nowadays, there are numerous recommendation approaches, like neighborhood-based approaches and model-based ones, and a lot of work on specific aspects of recommendations, like the cold start problem, the long tail problem and the evaluation of the recommended items in terms of a variety of parameters, like relevance, surprise and serendipity. Also, more recently, recommendations have more broad applications, beyond products, like news recommendations, links (friends) recommendations and more innovative ones like query recommendations and medicine recommendations.
In this course, we will focus on a number of approaches for producing recommendations, such as collaborative and content-based filtering, as well as more interactive and knowledge-based approaches. We will also discuss how to measure the effectiveness of recommender systems. Finally, we will cover emerging topics, such as contextual recommendations, recommendations for groups, packages recommendations, and how we can achieve diversity in recommender systems.
The first objective of this course is to present the scientific underpinnings of recommender systems. We will be concerned with basic concepts and more advanced techniques for producing recommendations. Our second objective is to provide to the student a comprehensive set of methods and approaches that can be exploited in the design and implementation of a specific recommender application.
Modes of study
Lectures, assignments, project, student presentations in class.
Preceding studies – Recommended
TIEP3 Data Bases, ITIA4 Introduction to Information Retrieval, TIETA17 Introduction to Big Data Processing, TIETS42 Databases and Information Retrieval Integration
Course Work and Assessment
Assignments (3) (30%)
Assignments will include exercise problems on the recommendation models studied, and short-answer questions on the papers and topics discussed in class.
Participation in the class.
The project will consist of the design and implementation of an innovative prototype for a recommender system in a specific application scenario, selected by the students. In addition to the implementation part, the project will be accompanied with a short paper (7-8 pages long), describing the proposed ideas.
The project will be evaluated at the end of the period. Extra points will be given to students with an exceptionally good project.