Infinite Mixtures of Markov Chains

  • Jan Reubold
  • Ahcène Boubekki
  • Thorsten Strufe
  • Ulf Brefeld
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10785)

Abstract

Facilitating a satisfying user experience requires a detailed understanding of user behavior and intentions. The key is to leverage observations of activities, usually the clicks performed on Web pages. A common approach is to transform user sessions into Markov chains and analyze them using mixture models. However, model selection and interpretability of the results are often limiting factors. As a remedy, we present a Bayesian nonparametric approach to group user sessions and devise behavioral patterns. Empirical results on a social network and an electronic text book show that our approach reliably identifies underlying behavioral patterns and proves more robust than baseline competitors.

Notes

Acknowledgements

This research has been funded in parts by the German Science Foundation DFG under grant GRK/1907 and by the German Federal Ministry of Education and Science BMBF under grant QQM/01LSA1503C.

References

  1. 1.
    Mitchell, A., Olmstead, K., Purcell, K., Rainie, L., Rosenstiel, T.: Understanding the participatory news consumer (2010)Google Scholar
  2. 2.
    Teh, Y.W., Jordan, M.I., Beal, M.J., Blei, D.M.: Hierarchical dirichlet processes. J. Am. Stat. Assoc. 101(476), 1566–1581 (2006)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Cadez, I., Heckerman, D., Meek, C., Smyth, P., White, S.: Visualization of navigation patterns on a web site using model-based clustering. In: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 280–284 (2000)Google Scholar
  4. 4.
    Ishwaran, H., Zarepour, M.: Exact and approximate sum representations for the dirichlet process. Can. J. Statistics/La Revue Canadienne de Statistique 30(2), 269–283 (2002)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Schreiber, W., Sochatzy, F., Ventzke, M.: Das multimediale Schulbuch - kompetenzorientiert, individualisierbar und konstruktionstransparent. In: Analyse von Schulbüchern als Grundlage empirischer Geschichtsdidaktik, pp. 212–232 (2013)Google Scholar
  6. 6.
    Pirolli, P.L., Pitkow, J.E.: Distributions of surfers’ paths through the world wide web: empirical characterizations. World Wide Web 2(1–2), 29–45 (1999)CrossRefGoogle Scholar
  7. 7.
    Manavoglu, E., Pavlov, D., Giles, C. L.: Probabilistic user behavior models. In: Third IEEE International Conference on Data Mining, ICDM 2003. IEEE (2003)Google Scholar
  8. 8.
    Ypma, A., Heskes, T.: Automatic categorization of web pages and user clustering with mixtures of hidden markov models. In: Zaïane, O.R., Srivastava, J., Spiliopoulou, M., Masand, B. (eds.) WebKDD 2002. LNCS (LNAI), vol. 2703, pp. 35–49. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-39663-5_3 CrossRefGoogle Scholar
  9. 9.
    Deshpande, M., Karypis, G.: Selective markov models for predicting web page accesses. ACM Trans. Internet Technol. (TOIT) 4(2), 163–184 (2004)CrossRefGoogle Scholar
  10. 10.
    Mochihashi, D., Sumita, E.: The infinite markov model. In: NIPS, pp. 1017–1024 (2007)Google Scholar
  11. 11.
    Bühlmann, P., Wyner, A.J.: Variable length markov chains. Ann. Stat. 27(2), 480–513 (1999)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Begleiter, R., El-Yaniv, R., Yona, G.: On prediction using variable order markov models. J. Artif. Intell. Res. 22, 385–421 (2004)MathSciNetMATHGoogle Scholar
  13. 13.
    Dubey, A., Hwang, S., Rangel, C., Rasmussen, C.E., Ghahramani, Z., Wild, D.L.: Clustering protein sequence and structure space with infinite gaussian mixture models. In: Pacific Symposium on Biocomputing, pp. 399–410 (2003)Google Scholar
  14. 14.
    Brown, D.P.: Efficient functional clustering of protein sequences using the dirichlet process. Bioinformatics 24(16), 1765–1771 (2008)CrossRefGoogle Scholar
  15. 15.
    Paul, T., Puscher, D., Strufe, T.: Improving the Usability of Privacy Settings in Facebook. CoRR (2011)Google Scholar
  16. 16.
    Du, N., Farajtabar, M., Ahmed, A., Smola, A.J., Song, L.: Dirichlet-Hawkes processes with applications to clustering continuous-time document streams. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 219–228 (2015)Google Scholar
  17. 17.
    Giraud, C.: Introduction to High-dimensional Statistics, vol. 138. CRC Press, Boca Raton (2014)MATHGoogle Scholar
  18. 18.
    Cocea, M., Weibelzahl, S.: Cross-system validation of engagement prediction from log files. In: Duval, E., Klamma, R., Wolpers, M. (eds.) EC-TEL 2007. LNCS, vol. 4753, pp. 14–25. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-75195-3_2 CrossRefGoogle Scholar
  19. 19.
    Salmeron-Majadas, S., Santos, O.C., Boticario, J.G.: Exploring indicators from keyboard and mouse interactions to predict the user affective state. In: Educational Data Mining (2014)Google Scholar
  20. 20.
    Kurihara, K., Welling, M., Teh, Y.W.: Collapsed variational dirichlet process mixture models. In: IJCAI 2007, pp. 2796–2801 (2007)Google Scholar
  21. 21.
    Olkin, I., Pratt, J.W.: Unbiased estimation of certain correlation coefficients. Ann. Math. Stat. 29(1), 201–211 (1958)MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Haider, P., Chiarandini, L., Brefeld, B.: Discriminative clustering for market segmentation. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM (2012)Google Scholar
  23. 23.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. Ser. B (methodological) 39(1), 1–38 (1977)MathSciNetMATHGoogle Scholar
  24. 24.
    Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. control 19(6), 716–723 (1974)MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    Schwarz, G.: Estimating the dimension of a model. Ann. Stat. 6(2), 461–464 (1978)MathSciNetCrossRefMATHGoogle Scholar
  26. 26.
    Roberts, G.O., Smith, A.: Simple conditions for the convergence of the gibbs sampler and metropolis-hastings algorithms. Stoch. Processes Appl. 49(2), 207–216 (1994)MathSciNetCrossRefMATHGoogle Scholar
  27. 27.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)MATHGoogle Scholar
  28. 28.
    Baker, F.B.: The basics of item response theory (2001). For full text: http://ericae.net/irt/baker
  29. 29.
    DeMars, C.: Item Response Theory. Oxford University Press, New York (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Jan Reubold
    • 1
  • Ahcène Boubekki
    • 2
  • Thorsten Strufe
    • 1
  • Ulf Brefeld
    • 2
  1. 1.TU DresdenDresdenGermany
  2. 2.Leuphana UniversityLüneburgGermany

Personalised recommendations