Caching Strategies for In-memory Neighborhood-based Recommender Systems

Simon Dooms, Toon De Pessemier, Luc Martens

2013

Abstract

Neighborhood-based recommender systems rely greatly on calculated similarity values to match interesting items with users in online information systems. Because sometimes there are too many similarity values or available memory is limited it is not always possible to calculate and store all these values in advance. Sometimes only a subset can be stored and recalculations cannot be avoided. In this work we focus on caching systems that optimize this trade-off between memory requirements and computational redundancy in order to speed up the recommendation calculation process. We show that similarity values are not equally important and some are used considerably more than others during calculation. We devised a caching strategy (referred to as SMART-cache) that incorporates this usage frequency knowledge and compared it with a basic least recently used (LRU) caching mechanism. Results showed total execution time could be reduced by a factor of 5 using LRU for a cache storing only 0.2% of the total number of similarity values. The speedup of the SMART approach on the other hand was less affected by the order in which user-item pairs were calculated.

References

  1. Herlocker, J., Konstan, J. A., and Riedl, J. (2002). An empirical analysis of design choices in neighborhoodbased collaborative filtering algorithms. Inf. Retr., 5(4):287-310.
  2. Jannach, D., Zanker, M., Felfernig, A., and Friedrich, G. (2011). Recommender Systems An Introduction. Cambridge University Press.
  3. Park, S.-T., Pennock, D., Madani, O., Good, N., and DeCoste, D. (2006). Naïve filterbots for robust cold-start recommendations. In Proc. ACM SIGKDD Conf. on Knowledge discovery and data mining (KDD 2006), pages 699-705, New York, NY, USA.
  4. Peralta, V. (2007). Extraction and integration of movielens and imdb data. Technical report, Technical Report, Laboratoire PRiSM, Université de Versailles, France.
  5. Qasim, U. (2011). Active Caching For Recommender Systems. PhD thesis, New Jersey Institute of Technology, New Jersey.
  6. Qasim, U., Oria, V., fang Brook Wu, Y., Houle, M. E., and O zsu, M. T. (2009). A partial-order based active cache for recommender systems. In Proc. ACM Conf. Recommender systems (RecSys 2009), pages 209-212.
  7. Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., and Riedl, J. (1994). Grouplens: an open architecture for collaborative filtering of netnews. In Proc. ACMF Conf. on Computer supported cooperative work (CSCW 7894), pages 175-186, New York, NY, USA. ACM.
  8. Seth, S. and Kaiser, G. (2011). Towards using cached data mining for large scale recommender systems. In Proc. Conf. Data Engineering and Internet Technology (DEIT 2011).
Download


Paper Citation


in Harvard Style

Dooms S., De Pessemier T. and Martens L. (2013). Caching Strategies for In-memory Neighborhood-based Recommender Systems . In Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-8565-54-9, pages 435-440. DOI: 10.5220/0004351704350440


in Bibtex Style

@conference{webist13,
author={Simon Dooms and Toon De Pessemier and Luc Martens},
title={Caching Strategies for In-memory Neighborhood-based Recommender Systems},
booktitle={Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2013},
pages={435-440},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004351704350440},
isbn={978-989-8565-54-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Caching Strategies for In-memory Neighborhood-based Recommender Systems
SN - 978-989-8565-54-9
AU - Dooms S.
AU - De Pessemier T.
AU - Martens L.
PY - 2013
SP - 435
EP - 440
DO - 10.5220/0004351704350440