-
Presentation
Presentation
This module provides the foundations for designing and implementing recommendation systems (RS). Students learn about different relevant algorithms, including collaborative filtering, which involves predicting user preferences based on similar users' preferences, and content-based recommendation. In addition to these fundamental topics, students also learn more advanced techniques such as hybrid RS, context-aware RS, using deep learning, and RS evaluation. The course has a theoretical-practical approach that includes implementing RS using real-world datasets, to gain practical experience with cutting-edge techniques. At the end of the course, students will have a deep understanding of the state-of-the-art in recommendation systems and will be able to apply these techniques to real-world problems.
-
Class from course
Class from course
-
Degree | Semesters | ECTS
Degree | Semesters | ECTS
Master Degree | Semestral | 7
-
Year | Nature | Language
Year | Nature | Language
2 | Optional | Português
-
Code
Code
ULHT6347-25233
-
Prerequisites and corequisites
Prerequisites and corequisites
Not applicable
-
Professional Internship
Professional Internship
Não
-
Syllabus
Syllabus
S1. Introduction to Recommender Systems S2. Collaborative Filtering S3. Content-Based Filtering S4. Hybrid Recommender Systems S5. Evaluation Metrics for Recommender Systems S6. Matrix Factorization S7. Deep Learning Approaches to Recommender Systems S8. Ethics and Social Implications of Recommender Systems
-
Objectives
Objectives
The the learning goals of the complements of recommendation systems module are: LG1. Understanding the fundamentals of recommendation systems, including their main challenges and applications LG2. Understanding and comparing different types of recommendation algorithms, including collaborative modelling, content-based, and hybrid LG3. Understanding the different evaluation metrics of recommendation systems and be able to evaluate the quality of a recommendation system LG4. Being able to design and implement a recommendation system, choosing the appropriate algorithm and adjusting parameters to achieve optimal performance LG5. Understanding the ethical and privacy issues involved in the implementation of recommendation systems and be aware of the social and economic implications of these systems
-
Teaching methodologies and assessment
Teaching methodologies and assessment
The teaching methods for this module aim to create an engaging and effective learning experience. Traditional lectures provide foundational knowledge, while in-class debates encourage active participation and critical thinking. Retrieval self-assessments improve long-term retention of information, allowing students to monitor their learning progress and identify areas for improvement. The combination of lectures, debates, and self-assessment activities creates a well-rounded learning experience that meets the needs of all students and helps them develop the skills and knowledge to succeed as data scientists.
-
References
References
Introduction to Recommender Systems by Aggarwal, C. C. (2016)
-
Office Hours
Office Hours
-
Mobility
Mobility
No
