A recommender system is software that suggests items that are likely to be of interest to the user. These recommendations are personalised according to a user model or user profile. The task is a task of information filtering: what of all possible items are interesting to this particular user?

The methods applied stem in particular from the areas of machine learning, information retrieval and language technology. The main approaches for recommender systems are collaborative filtering (recommend items that users with similar tastes preferred in the past) and content-based filtering (recommend items similar to the ones the user preferred in the past).

Each student will search additional literature, write a seminar paper (10-15 pages) and present it in a seminar session. In addition, the students are required to attend presentation sessions and comment on the texts of other students. To pass the seminar, you need to attend at least ¾ of the sessions. The language of the seminar is English.

The model for the latex document can be found here (file engl_malli.tex). The presentation should be 30-45 minutes long.

The final number of sessions depends on the number of persons attending the seminar (tba).

Overview books:

• D. Janach, M. Zanker, A. Felfering and G. Friedrich: Recommender Systems – An Introduction. Cambridge University Press, Cambridge, 2011. (below denoted RS)
• F. Ricci, L. Rokach, B. Shapira and P. B. Kantor (eds.): Recommender Systems Handbook. Springer Verlag, New York, 2011. (below denoted RSH)

Overview article:

• G. Adomavicius and A. Tuzhlin: Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extension, IEEE Trans. Knowledge and Data Engineering 17(2005)6(June), 734-749.

List of sessions:

• 5.9. Introduction and division of topics. Introductory slides by Patrik (note that the meeting dates were updated in the session, those mentioned here are the final ones)
• 12.9.no seminar
• 19.9. no seminar
• 26.9. Collaborative recommendations
• 3.10. Content-based recommendations
• 10.10. POSTPONED DO TO ILLNESS. NO SEMINAR.
• 31.10.  PRESENTER WITHDRAWN FROM SEMINAR. NO SEMINAR.
• 7.11. Knowledge-based recommendations
• 14.11. Context-aware recommender systems
• 21.11. NO SEMINAR.
• 28.11. Evaluation of recommender systems

 Collaborative recommendations: Chapter 2 in RS and Chapter 5 in RSH.

• Content-based recommendations: Chapter 3 in RS and Chapter 3 in RSH;
  M. J. Pazzani and D. Billsus: Content-based recommendation systems, The Adaptive Web, Lecture Notes in Computer Science 4321, Springer-Verlag, Berlin, 2007, 325-341.
• Knowledge-based recommendations (including critiquing recommenders): Chapters 4 and 13 in RS;
  R. Burke: Knowledge-based recommender systems, Encyclopedia of Library and Information Science 69(2000)32, 180-200.
• Hybrid recommender systems: Chapter 5 in RS;
  R. Burke: Hybrid recommender systems: survey and experiments, User-Modeling and User-Adapted Interaction 12(2002)4, 331-370.
• Recommender systems for books, movies, videos:
  G. Linden, B. Smith and J. York: Amazon.com recommendations – item-to-item collaborative filtering, IEEE Internet Computing 7(2003)1(January-February), 76-80;
  Y. Koren, R. Bell and C: Volinsky: Matrix factorization techniques for recommender systems, Computer 42(2009)8(August), 42-49. (about the Netflix competition);
  Y. Koren: The BellKor Solution to the Netflix Grand Prize, August 2009;
  J. Davidson, B. Liebald, J. Liu, P. Nandy and T. Van Vleet: The YouTube video recommendation system, Proc. RecSys 2010, 293-296.
• Using social networks for recommendations:
  I .Guy et al.: Personalized recommendation of social software items based on social relations, Proc. RecSys 2009, 53-60;
  J. Hannon, M. Bennett and B. Smyth: Recommending twitter users to follow using content and collaborative filtering approaches, Proc. RecSys 2010, 199-206;
  P. Symeonidis, E. Tiakas and Y. Manolopoulos: Transivite node similarity for link prediction in social networks with positive and negative links, Proc. RecSys 2010, 183-190.
• Explanations in recommender systems: Chapter 6 in RS abd Chapter 15 in RSH;
  J. L. Herlocker, J. A. Konstan and J. Riedl: Explaining collaborative filtering recommendations, Proc. CSCW’00, 241-250.
• Context-aware recommender systems: Chapter 12 in RS and Chapter 7 in RSH.
• Evaluation of recommender systems: Chapter 7 in RS and Chapter 8 in RSH;
  J L. Herlocker, J. A. Konstan, L. G. Terveen and J. T. Reidl: Evaluating collaborative filtering recommendation systems, ACM Transactions on Information Systems 22 (2004)1(January), 5-53;
  F. H. Del Olmo and E. Gaudioso: Evaluation of recommender systems: a new approach, Expert Systems with Applications 35(2008), 790-804;
  G. Adomavicius and J. Zhang: On the stability of recommendation algorithms, Proc. RecSys 2010, 47-54.