Adaptation and Evaluation of Recommendations for Short-term Shopping Goals

ABSTRACT

An essential characteristic in many e-commerce settings is that website visitors can have very specific short-term shopping goals when they browse the site. Relying solely on long-term user models that are pre-trained on historical data can therefore be insufficient for a suitable next-basket recommendation. Simple "real-time" recommendation approaches based, e.g., on unpersonalized co-occurrence patterns, on the other hand do not fully exploit the available information about the user's long-term preference profile. In this work, we aim to explore and quantify the effectiveness of using and combining long-term models and short-term adaptation strategies. We conducted an empirical evaluation based on a novel evaluation design and two real-world datasets. The results indicate that maintaining short-term content-based and recency-based profiles of the visitors can lead to significant accuracy increases. At the same time, the experiments show that the choice of the algorithm for learning the long-term preferences is particularly important at the beginning of new shopping sessions.

References

1. G. Adomavicius and A. Tuzhilin. Context-aware recommender systems. In Recommender Systems Handbook, pages 217--253. 2011.
2. S. R. Aghabozorgi and T. Y. Wah. Recommender systems: Incremental clustering on web log data. In Proc. ICIS '09, pages 812--818, 2009.
3. Y. AlMurtadha, N. B. Sulaiman, N. Mustapha, N. I. Udzir, and Z. Muda. ARS: Web page recommendation system for anonymous users based on web usage mining. In Proc. ECS '10, pages 115--120, 2010.
4. S. Anand and B. Mobasher. Contextual recommendation. In From Web to Social Web, volume 4737 of LNCS, pages 142--160. 2007.
5. L. Baltrunas and X. Amatriain. Towards time-dependant recommendation based on implicit feedback. In Proc. CARS WS at RecSys '09, 2009.
6. L. Baltrunas, B. Ludwig, and F. Ricci. Context relevance assessment for recommender systems. In Proc. IUI '11, pages 287--290, 2011.
7. P. G. Campos, F. Dıez, and I. Cantador. Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols. UMUAI, 24(1--2):67--119, 2014.
8. P. Cremonesi, F. Garzotto, S. Negro, A. Papadopoulos, and R. Turrin. Looking for "good" recommendations: A comparative evaluation of recommender systems. In Proc. Interact '11, pages 152--168, 2011.
9. P. Cremonesi, F. Garzotto, and R. Turrin. Investigating the persuasion potential of recommender systems from a quality perspective: An empirical study. ACM TIST, 2(2):11:1--11:41, 2012.
10. P. Cremonesi, Y. Koren, and R. Turrin. Performance of algorithms on top-n recommendation tasks. In Proc. RecSys '10, pages 39--46, 2010.
11. M. B. Dias, D. Locher, M. Li, W. El-Deredy, and P. J. Lisboa. The value of personalised recommender systems to e-business: A case study. In Proc. RecSys '08, pages 291--294, 2008.
12. N. Hariri, B. Mobasher, and R. Burke. Context adaptation in interactive recommender systems. In Proc. RecSys '14, pages 41--48, 2014.
13. J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl. Evaluating collaborative filtering recommender systems. ACM TOIS, 22(1):5--53, 2004.
14. Y. Hu, Y. Koren, and C. Volinsky. Collaborative filtering for implicit feedback datasets. In Proc. ICDM '08, pages 263--272, 2008.
15. D. Jannach and K. Hegelich. A case study on the effectiveness of recommendations in the mobile internet. In Proc. RecSys '09, pages 205--208, 2009.
16. D. Jannach, L. Lerche, F. Gedikli, and G. Bonnin. What recommenders recommend - an analysis of accuracy, popularity, and sales diversity effects. In Proc. UMAP '13, pages 25--37, 2013.
17. D. Jannach, M. Zanker, M. Ge, and M. Gröning. Recommender systems in computer science and information systems - a landscape of research. In Proc. EC-Web '12, pages 76--87, 2012.
18. E. Kirshenbaum, G. Forman, and M. Dugan. A live comparison of methods for personalized article recommendation at Forbes.com. In Proc. ECML/PKDD '12, pages 51--66, 2012.
19. Y. Koren. Collaborative filtering with temporal dynamics. In Proc. KDD '09, pages 447--456, 2009.
20. L. Lerche and D. Jannach. Using graded implicit feedback for bayesian personalized ranking. In Proc. RecSys '14, pages 353--356, 2014.
21. J. Liu, P. Dolan, and E. R. Pedersen. Personalized news recommendation based on click behavior. In Proc. IUI '10, pages 31--40, 2010.
22. B. Mobasher, H. Dai, T. Luo, and M. Nakagawa. Using sequential and non-sequential patterns in predictive web usage mining tasks. In Proc. ICDM '02, pages 669--672, 2002.
23. Q. N. Nguyen and F. Ricci. Long-term and session-specific user preferences in a mobile recommender system. In Proc. IUI '08, pages 381--384, 2008.
24. S. Rendle. Factorization machines with libFM. ACM Transactions on Intelligent Systems Technology, 3(3):57:1--57:22, 2012.
25. S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. BPR: Bayesian personalized ranking from implicit feedback. In Proc. UAI '09, pages 452--461, 2009.
26. S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. Factorizing personalized markov chains for next-basket recommendation. In Proc.WWW '10, pages 811--820. ACM, 2010.
27. F. Ricci, A. Venturini, D. Cavada, N. Mirzadeh, D. Blaas, and M. Nones. Product recommendation with interactive query management and twofold similarity. In Proc. ICCBR '03, pages 479--493, 2003.
28. A. Said, D. Tikk, K. Stumpf, Y. Shi, M. Larson, and P. Cremonesi. Recommender systems evaluation: A 3D benchmark. In Proc. RUE WS at RecSys '12, pages 21--23, 2012.
29. E. Shen, H. Lieberman, and F. Lam. What am I gonna wear?: Scenario-oriented recommendation. In Proc. IUI '07, pages 365--368, 2007.
30. Y. Shi, A. Karatzoglou, L. Baltrunas, M. Larson, and A. Hanjalic. xCLiMF: optimizing expected reciprocal rank for data with multiple levels of relevance. In Proc. RecSys '13, pages 431--434, 2013.
31. M. Tavakol and U. Brefeld. Factored MDPs for detecting topics of user sessions. In Proc. RecSys '14, pages 33--40, 2014.
32. M. Zanker, M. Bricman, S. Gordea, D. Jannach, and M. Jessenitschnig. Persuasive online-selling in quality & taste domains. In Proc. EC-Web '06, pages 51--60, 2006.

Index Terms

• Information systems

  • Information retrieval

    • Retrieval tasks and goals

      • Document filtering

      • Information extraction