Module Details

Module Code: COMP9065
Title: Recommender Systems
Long Title: Recommender Systems
NFQ Level: Expert
Valid From: Semester 1 - 2018/19 ( September 2018 )
Duration: 1 Semester
Credits: 5
Field of Study: 4811 - Computer Science
Module Delivered in: 1 programme(s)
Module Description: AI-based recommender systems are widely used across a broad range of domains including e-commerce, marketing, movie/music recommendations, etc. In this applied module, learners will focus on a number of case studies and will develop recommender systems for these specific problem domains. The module will demonstrate how to analyse a problem domain and subsequently design, implement and integrate into an appropriate recommender system, with a focus on collaborative, content-based filtering and hybrid recommender systems. Students will develop and evaluate their own recommender system for a real-world case study.
 
Learning Outcomes
On successful completion of this module the learner will be able to:
# Learning Outcome Description
LO1 Assess the use of recommender systems across a range of daily life applications and the challenges in developing a fine-tuned recommender system.
LO2 Critically assess and select a recommender system for a given problem.
LO3 Design a recommender system applying either a content-based or collaborative filtering approach.
LO4 Develop and implement recommender systems using open source tools.
LO5 Evaluate the performance of different recommender systems on a sample dataset.
Dependencies
Module Recommendations

This is prior learning (or a practical skill) that is strongly recommended before enrolment in this module. You may enrol in this module if you have not acquired the recommended learning but you will have considerable difficulty in passing (i.e. achieving the learning outcomes of) the module. While the prior learning is expressed as named MTU module(s) it also allows for learning (in another module or modules) which is equivalent to the learning specified in the named module(s).
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this module. You may not earn additional credit for the same learning and therefore you may not enrol in this module if you have successfully completed any modules in the incompatible list.
No incompatible modules listed
Co-requisite Modules
No Co-requisite modules listed
Requirements

This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed. You may not enrol on this module if you have not acquired the learning specified in this section.
No requirements listed
 
Indicative Content
Introduction to recommender systems
History of recommender systems and their usee in the e-services industry. Information search and retrieval, filtering and personalising data content. Recommender system model - items, users and transactions. Item/user categorisation and characterisation. Utility matrices.
General recommender system approaches
Introduction to content-based filtering, collaborative filtering, data mining methods, context-aware methods (demographics, temporal, location, knowledge-based). Development of content-based filtering techniques. High-level architecture. Item similarity and user profiles.
Collaborative filtering
General framework. User similarity. Matrix factorisation, alternating least squares, neighbourhood-based methods. Challenges associated with collaborative filtering, and possible solutions: cold-start, data sparsity, etc. Hybrid collaborative filtering and content-based filtering methods: Combining content-based and collaborative filtering in order to overcome disadvantages of both.
Tools and applications
Using open source tools to build and evaluate content-based and collaborative filtering recommender systems. Application domains. Recommender systems will be built for two test cases using widely-studied datasets.
Evaluating recommender systems
Data sampling techniques. Offline and online evaluation of recommendation system performance and scalability, parameter tuning and calibration. Metrics for evaluation of recommendation quality: Prediction accuracy, rank accuracy. Recommendation system properties such as diversity, robustness, serendipity. Security for recommendation systems: limiting influence of malicious users.
Module Content & Assessment
Assessment Breakdown%
Coursework100.00%

Assessments

Coursework
Assessment Type Project % of Total Mark 40
Timing Week 8 Learning Outcomes 1,2,3,4
Assessment Description
The student will design and implement a recommender system for a sample data set, and produce a report outlining the steps taken and the basis for their choice of recommender system approach.
Assessment Type Project % of Total Mark 60
Timing Sem End Learning Outcomes 2,3,4,5
Assessment Description
The student will design and implement two recommender systems on a dataset. The student will produce a report comparing and contrasting the performance of the two methods in terms of both accuracy and recommender system properties.
No End of Module Formal Examination
Reassessment Requirement
Coursework Only
This module is reassessed solely on the basis of re-submitted coursework. There is no repeat written examination.

The University reserves the right to alter the nature and timings of assessment

 

Module Workload

Workload: Full Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Lectures delivering theory underpinning learning outcomes. Every Week 2.00 2
Lab Contact Practical to develop recommender system. Every Week 2.00 2
Independent Learning Non Contact Student undertakes independent study. The student reads recommended papers and practices implementation. Every Week 3.00 3
Total Hours 7.00
Total Weekly Learner Workload 7.00
Total Weekly Contact Hours 4.00
Workload: Part Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Lecture delivering theory underpinning learning outcomes. Every Week 2.00 2
Lab Contact Practical to develop recommender system. Every Week 2.00 2
Independent Learning Non Contact Student undertakes independent study. The student reads recommended papers and practices implementation. Every Week 3.00 3
Total Hours 7.00
Total Weekly Learner Workload 7.00
Total Weekly Contact Hours 4.00
 
Module Resources
Recommended Book Resources
  • Charu C. Aggarwal. (2016), Recommender Systems: The Textbook, Springer, [ISBN: 9783319296579].
Supplementary Book Resources
  • Dietmar Jannach, Markus Zanker, Alexander Felfernig, Gerhard Friedrich. (2010), Recommender Systems: An Introduction, Cambridge University Press, [ISBN: 9780521493369].
  • Francesco Ricci, Lior Rokach, Bracha Shapira. (2015), Recommender Systems Handbook, 2. 28, Springer, [ISBN: 9781489976376].
This module does not have any article/paper resources
Other Resources
 
Module Delivered in
Programme Code Programme Semester Delivery
CR_KARIN_9 Master of Science in Artificial Intelligence 1 Elective