Short Course: Recommendation Tools,
Spring 2016
News
-
Update: The final project deadline is extended to June 6. Please submit the project (code and report) before midnight June 6 (CET).
Course Description
This course will introduce recommender system techniques and focus on the R package recommenderlab. We will cover non-personalized, content-based and collaborative methods for producing recommendations. The students will learn how to prepare data, how to perform experiments using different recommendation strategies, and how to evaluate the recommendation quality.
Prerequisites:
Basic R skills.
Outline
Day 1: Introduction
- Overview [slides]
- Taxonomy and design space
- Exercise 1: Design Space [template] (finish after class and turn in via email)
- Content-based recommendations
[code]
- Exercise 2: Analyze content profiles
[template]
(finish after class and turn in via email)
Day 2: Tools
Day 3: Recommendation methods
- User-based collaborative filtering
[code]
- Item-based collaborative filtering
[code]
- Matrix factorization
[code]
- Exercise 3: Rate 20 movies (from the MovieLense dataset),
create recommendations and
evaluate the recommendation quality
[template]
(finish after class and turn in via email)
- Work on project
Day 4: Evaluation and other topics
- Presentation of Exercise 3
- Evaluation of recommender algorithms
[code]
- Cold start problem
- Explanation of recommendations
- Threat models
- Hybrid recommender systems
[code]
- Work on project
- Presentation of prototypes
Reading List and Textbook
Mandatory pre-class reading list
- Paul Resnick and Hal R. Varian. 1997. Recommender systems. Commun. ACM 40, 3 (March 1997), 56-58. Link
- Francesco Ricci, Lior Rokach and Bracha Shapira. 2010.
Introduction to Recommender Systems
Handbook.
Link
More reading
-
Xiaoyuan Su and Taghi M. Khoshgoftaar. 2009. A survey of collaborative filtering techniques. Adv. in Artif. Intell. 2009, Article 4 (January 2009). Link
-
Jonathan L. Herlocker, Joseph A. Konstan, and John Riedl. 2000. Explaining collaborative filtering recommendations. In Proceedings of the 2000 ACM conference on Computer supported cooperative work (CSCW '00). ACM, New York, NY, USA, 241-250. Link
-
Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2000. Analysis of recommendation algorithms for e-commerce. In Proceedings of the 2nd ACM conference on Electronic commerce (EC '00). ACM, New York, NY, USA, 158-167. Link
-
Y. Koren, R. Bell and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems," in Computer, vol. 42, no. 8, pp. 30-37, Aug. 2009.
Link
-
M. Hahsler, "An Introduction to the R package recommenderlab," Link
Text book (optional)
-
Recommender Systems: An Introduction by Dietmar Jannach, Markus Zanker, Alexander Felfernig, Gerhard Friedrich, 2010, ISBN-10: 0521493366, Cambridge University Press
Grading
- Exercise 1: 15%
- Exercise 2: 15%
- Exercise 3: 15%
- Class paper/project: 55%
Software and Data Used in Class
Example Recommender Systems
Learning resources
Michael Hahsler
Last modified: