Module COMP54215: Recommender Systems

Department: Computer Science

COMP54215: Recommender Systems

Prerequisites

• None

Corequisites

• None

Excluded Combination of Modules

• None

Aims

• To introduce students to recommender systems’ techniques and approaches to evaluate them.
• To enable students to develop user profiles based on user demographics, behaviour, preferences, contextual information, etc.
• To train students to design and implement methods for predicting and recommending the most relevant and tailored content to an individual user.

Content

• Levels of personalization; non-personalised recommenders.
• Content-based filtering.
• Collaborative filtering.
• Hybrid schemes.
• Context-aware recommenders.
• Knowledge-based and group recommenders.
• Conventional vs. state-of-the-art methods (e.g., deep learning in RS).
• Evaluation methods.
• Trends in RSs (e.g., cross-domain recommendations, fairness, popularity bias, etc.).
• Ethical issues in recommender systems.

Learning Outcomes

• By the end of this module, students should be able to demonstrate:
• a critical understanding of the different types of recommender systems, their purpose and domains of application.
• an understanding of recommender system users: interaction behaviour, demographics, preferences, contextual information.
• an in-depth knowledge of recommender system algorithms.
• a systematic understanding of recommender system evaluation methods.

• By the end of this module, students should be able to demonstrate:
• an ability to undertake self-study and independent research in recommender system concepts, state-of-the-art techniques, and exploration of potential for further developments.
• an ability to apply conventional and state-of-the-art RS methods and techniques, but particularly content-based, collaborative, and hybrid recommender systems techniques.
• an ability to implement a recommender system for a specific domain.
• an ability to evaluate the performance of different recommender systems, including any ethical issues they might cause.

• By the end of this module, students will be able to demonstrate:
• an ability to critically analyse and evaluate current practices and recent advances in Computer Science and IT.
• an ability to identify the applicability of Computer Science methods to resolve challenges or achieve goals in a specific domain.
• an ability to practically implement Computer Science techniques/methods.
• an ability to work in teams and perform peer-review.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Lectures enable the students to learn new material relevant to recommender system concepts, methods, advances and their applications in different domains.
• Computer classes enable students to apply their learning to practical examples.
• Formative and summative assessments assess the knowledge in core recommender system concepts and application of the related methods and techniques.
• The assignment element of the coursework component consists of a coding exercise with accompanying report.
• The teacher-supervisor review element of the coursework component consists of student engagement in the course.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Formative assignments are given during the module.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University