Fuzzy Fingerprints for Item-Based Collaborative Filtering

  • André CarvalhoEmail author
  • Pável Calado
  • Joao Paulo Carvalho
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 641)


Memory-based Collaborative filtering solutions are dominant in the Recommender Systems domain, due to its low implementation effort and service maintenance when compared with Model-based approaches. Memory-based systems often rely on similarity metrics to compute similarities between items (or users). Such metrics can be improved either by improving comparison quality or minimizing computational complexity. There is, however, an important trade-off—in general, models with high complexity, which significantly improve recommendations, are computationally unfeasible for real-world applications. In this work, we approach this issue, by applying Fuzzy Fingerprints to create a novel similarity metric for Collaborative Filtering. Fuzzy Fingerprints provide a concise representation of items, by selecting a relatively small number of user ratings and using their order to describe them. This metric requires from 23% through 95% less iterations to compute the similarities required for a rating prediction, depending on the density of the dataset. Despite this reduction, experiments performed in three datasets show that our metric is still able to have comparable recommendation results, in relation to state-of-art similarity metrics.



This work was supported by national funds through Fundação para a Ciência e a Tecnologia (FCT) with reference UID/CEC/50021/2013, by project GoLocal (ref. CMUPERI/TIC/0046/2014) and co-financed by the University of Lisbon and INESC-ID.


  1. 1.
    Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17(6), 734–749 (2005). doi: 10.1109/TKDE.2005.99 CrossRefGoogle Scholar
  2. 2.
    Bobadilla, J., Ortega, F., Hernando, A., Gutiérrez, A.: Recommender systems survey. Knowl. Based Syst. 46, 109–132 (2013). doi: 10.1016/j.knosys.2013.03.012. CrossRefGoogle Scholar
  3. 3.
    Bobadilla, J., Ortega, F., Hernando, A., de Rivera, G.G.: A similarity metric designed to speed up, using hardware, the recommender systems k-nearest neighbors algorithm. Knowl. Based Syst. 51, 27–34 (2013). doi: 10.1016/j.knosys.2013.06.010. CrossRefGoogle Scholar
  4. 4.
    Bobadilla, J., Serradilla, F., Bernal, J.: A new collaborative filtering metric that improves the behavior of recommender systems. Knowl. Based Syst. 23(6), 520–528 (2010). doi: 10.1016/j.knosys.2010.03.009. CrossRefGoogle Scholar
  5. 5.
    Chen, S., Luo, T., Liu, W., Xu, Y.: Incorporating similarity and trust for collaborative filtering. In: Sixth International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009, vol. 2, pp. 487–493 (2009). doi: 10.1109/FSKD.2009.720
  6. 6.
  7. 7.
    Homem, N., Carvalho, J.P.: Authorship identification and author fuzzy “fingerprints”. In: 2011 Annual Meeting of the North American Fuzzy Information Processing Society (NAFIPS), pp. 1–6 (2011). doi: 10.1109/NAFIPS.2011.5751998
  8. 8.
    Koenigstein, N., Koren, Y.: Towards scalable and accurate item-oriented recommendations. In: Proceedings of the 7th ACM Conference on Recommender Systems, RecSys 2013, pp. 419–422. ACM, New York (2013). doi: 10.1145/2507157.2507208
  9. 9.
    Liu, H., Hu, Z., Mian, A., Tian, H., Zhu, X.: A new user similarity model to improve the accuracy of collaborative filtering. Knowl. Based Syst. 56, 156–166 (2014). doi: 10.1016/j.knosys.2013.11.006. CrossRefGoogle Scholar
  10. 10.
    Pereira, R., Lopes, H., Breitman, K., Mundim, V., Peixoto, W.: Cloud based real-time collaborative filtering for item-item recommendations. Comput. Ind. 65(2), 279–290 (2014). doi: 10.1016/j.compind.2013.11.005. CrossRefGoogle Scholar
  11. 11.
    Said, A., Bellogín, A.: Rival: a toolkit to foster reproducibility in recommender system evaluation. In: Proceedings of the 8th ACM Conference on Recommender Systems, RecSys 2014, pp. 371–372. ACM Press (2014). doi: 10.1145/2645710.2645712
  12. 12.
    Son, L.H.: HU-FCF: a hybrid user-based fuzzy collaborative filtering method in recommender systems. Exp. Syst. Appl. 41(15), 6861–6870 (2014). doi: 10.1016/j.eswa.2014.05.001 CrossRefGoogle Scholar
  13. 13.
    Tsai, C.F., Hung, C.: Cluster ensembles in collaborative filtering recommendation. Appl. Soft Comput. 12(4), 1417–1425 (2012). doi: 10.1016/j.asoc.2011.11.016 CrossRefGoogle Scholar
  14. 14.
    Vijayakumar, V., Neelanarayanan, V., Bagchi, S.: Big data, cloud and computing challenges performance and quality assessment of similarity measures in collaborative filtering using mahout. Procedia Comput. Sci. 50, 229–234 (2015). doi: 10.1016/j.procs.2015.04.055. CrossRefGoogle Scholar
  15. 15.
    Xu, R., Wang, S., Zheng, X., Chen, Y.: Distributed collaborative filtering with singular ratings for large scale recommendation. J. Syst. Softw. 95, 231–241 (2014). doi: 10.1016/j.jss.2014.04.045. CrossRefGoogle Scholar
  16. 16.
    Ye, T., Bickson, D., Ampazis, N., Benczur, A.: LSRS’15: Workshop on large-scale recommender systems. In: Proceedings of the 9th ACM Conference on Recommender Systems, RecSys 2015, pp. 349–350. ACM, New York (2015). doi: 10.1145/2792838.2798715
  17. 17.
    Yera, R., Castro, J., Martínez, L.: A fuzzy model for managing natural noise in recommender systems. Appl. Soft Comput. 40, 187–198 (2016). doi: 10.1016/j.asoc.2015.10.060. CrossRefGoogle Scholar
  18. 18.
    Zheng, M., Min, F., Zhang, H.R., Chen, W.B.: Fast recommendations with the m-distance. IEEE Access 4, 1464–1468 (2016). doi: 10.1109/ACCESS.2016.2549182 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • André Carvalho
    • 1
    Email author
  • Pável Calado
    • 1
  • Joao Paulo Carvalho
    • 1
  1. 1.INESC-ID, Instituto Superior TécnicoUniversidade de LisboaLisboaPortugal

Personalised recommendations