HOMMIT: A Sequential Recommendation for Modeling Interest-Transferring via High-Order Markov Model

  • Yang Xu
  • Xiaoguang HongEmail author
  • Zhaohui Peng
  • Yupeng Hu
  • Guang Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10570)


Capturing user interest accurately is a key task for predicting personalized sequential action in recommender systems. Through preliminary investigation, we find that user interest is stable in short term, while changeable in long term. The user interest changes significantly during the interaction with the system, and the duration of a particular interest and the frequency of transition are also personalized. Based on this finding, a recommendation framework called HOMMIT is proposed, which can identify user interests and adapt an improved high-order Markov chain method to model the dynamic transition process of user interests. It can predict the transition trends of user interest and make personalized sequential recommendation. We evaluate and compare multiple implementations of our framework on two large, real-world datasets. The experiments are conducted to prove the high accuracy of our proposed sequential recommendation framework, which verified the importance of considering interest-transferring in recommendations.


Interest modeling Recommender system Markov model 



This work is supported by NSF of China (No. 61602237), the Science and Technology Development Plan of Shandong, China (Nos. 2014GGX101047, 2014GGX101019).


  1. 1.
    Karypis, G.: Evaluation of item-based top-N recommendation algorithms. In: CIKM 2001, pp. 247–254 (2001)Google Scholar
  2. 2.
    Ding, Y., Li, X.: Time weight collaborative filtering. In: CIKM 2005, pp. 485–492 (2005)Google Scholar
  3. 3.
    Raftery, A.E.: A model for high-order markov chains. J. Roy. Stat. Soc. 47(3), 528–539 (1985)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Deshpande, M., Karypis, G.: Item-based top-N recommendation algorithms. ACM TOIS 22(1), 143–177 (2004)CrossRefGoogle Scholar
  5. 5.
    Xu, Y., Hong, X., Peng, Z., Yang, G., Yu, P. S.: Temporal recommendation via modeling dynamic interests with inverted-U-Curves. In: DASFAA 2016, pp. 313–329 (2016)CrossRefGoogle Scholar
  6. 6.
    Chen, J., Wang, C., Wang, J.: Modeling the interest-forgetting curve for music recommendation. In: MM 2014, pp. 921–924 (2014)Google Scholar
  7. 7.
    Toscher, A., Jahrer, M., Bell, R. M.: The BigChaos solution to the Netflix Grand prize (2008)Google Scholar
  8. 8.
    Chen, J., Wang, C., Wang, J.: A personalized interest-forgetting markov model for recommendations. In: AAAI 2015, pp. 16–22 (2015)Google Scholar
  9. 9.
    Koychev, I., Schwab, I.: Adaptation to drifting user’s interests. In: ECML 2000 Workshop: Machine Learning in New Information Age (2000)Google Scholar
  10. 10.
    Rendle, S., Freudenthaler, C., Schmidt-Thieme, L.: Factorizing personalized Markov chains for next-basket recommendation. In: WWW 2010, pp. 811–820 (2010)Google Scholar
  11. 11.
    He, R., Mcauley, J.: Fusing similarity models with markov chains for sparse sequential recommendation. In: ICDM 2016, pp. 191–200 (2016)Google Scholar
  12. 12.
    Cheng, C., Yang, H., Lyu, M.R., King, I.: Where you like to go next: successive point-of-interest recommendation. In: IJCAI, pp. 2605–2611 (2013)Google Scholar
  13. 13.
    Yin, B., Yang, Y., Liu, W.: Exploring social activeness and dynamic interest in community-based recommender system. In: WWW 2014, pp. 771–776 (2014)Google Scholar
  14. 14.
    Jolliffe, I.T.: Pincipal component analysis. J. Mark. Res. 25, 513 (2002)Google Scholar
  15. 15.
  16. 16.
  17. 17.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Yang Xu
    • 1
  • Xiaoguang Hong
    • 1
    Email author
  • Zhaohui Peng
    • 1
  • Yupeng Hu
    • 1
  • Guang Yang
    • 1
  1. 1.School of Computer Science and TechnologyShandong UniversityJinanPeople’s Republic of China

Personalised recommendations