Skip to main content

A Time-aware Hybrid Algorithm for Online Recommendation Services

Abstract

With the rapid development of cloud computing technology, online recommendation services have been a new trend for providing specific information on topics such as lifestyle, fashion news and a variety of other activities. Recommendation algorithm is crucially important for the delivery of personalized services to users. Currently, the key important problem is how to improve the quality of online recommendation services. To solve the problem of goods popularity bias, this paper introduces the prevalence of items into user interest model, and proposes an item popularity model based on user interest feature. Usually, traditional models do not consider the stable of users’ interests, which may make it hard to capture their interest. To deal with the above situation, we propose a time-sensitive and stable interest similarity model to calculate the similarity of user interest. Furthermore, a novel algorithm termed as item popularity similarity with time sensitivity (IPSTS)is proposed by combining the above two kinds of similarity model, and they are assigned different weight factors to balance their impacts. In this paper, we conduct the comparative experiments to evaluate the proposed approach and the traditional collaborative filtering algorithms. The final experimental results indicate that IPSTS can effectively reduce the value of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE).

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. 1.

    Ding S, Yang S, Zhang Y, et al. (2014) Combining QoS prediction and customer satisfactionestimation to solve cloud service trustworthiness evaluation problems. Knowl Based Syst 56:216–225. https://doi.org/10.1016/j.knosys.2013.11.014

    Article  Google Scholar 

  2. 2.

    Leem B, Chun H (2014) An impact of online recommendation network on demand. Expert Syst Appl 41:1723–1729. https://doi.org/10.1016/j.eswa.2013.08.071

    Article  Google Scholar 

  3. 3.

    Liao YS, Lu JY, Liu DR (2019) News recommendation based on collaborative semantic topic models and recommendation adjustment. In: International conference on machine learning and cybernetics (ICMLC), pp 1–6. https://doi.org/10.1109/ICMLC48188.2019.8949259

  4. 4.

    Xue H, Zhang DM (2019) A recommendation model based on content and social network. In: 2019 IEEE 8th Joint international information technology and artificial intelligence conference (ITAIC), pp 477–481. https://doi.org/10.1109/ITAIC.2019.8785729

  5. 5.

    Roy S, Sharma M, Singh SK (2019) Movie recommendation system using semi-supervised learning. In: 2019 Global conference for advancement in technology (GCAT), pp 1–5. https://doi.org/10.1109/GCAT47503.2019.8978353

  6. 6.

    Liu DR, Chen KY, Chou YC, Lee JH (2017) An online activity recommendation approach based on the dynamic adjustment of recommendation lists. In: 2017 6th IIAI international congress on advanced applied informatics (IIAI-AAI), pp 407–412. https://doi.org/10.1109/IIAI-AAI.2017.60

  7. 7.

    Anonymous (2015) Statistical report on internet development in China. Internet Communication 35(7):54–59

    Google Scholar 

  8. 8.

    Leskovec J, Rajaraman A, Ullman J (2014) Mining of massive datasets, 2nd. Cambridge University Press, Cambridge, pp 108–138. https://doi.org/10.1017/cbo9781139058452.005

    Book  Google Scholar 

  9. 9.

    Lai CH, Liu DR, Lin CS (2013) Novel personal and group-based trust models in collaborative filtering for document recommendation. Inform Sci 239:31–49. https://doi.org/10.1016/j.ins.2013.03.030

    Article  Google Scholar 

  10. 10.

    Li D, Lv Q, Shang L, Gu N (2014) Item-based top-N recommendation resilient to aggregated information revelation. Knowl Based Syst 67:290–304. https://doi.org/10.1016/j.knosys.2014.04.038

    Article  Google Scholar 

  11. 11.

    Ding S, Wang Z, Wu D, Olson DL (2017) Utilizing customer satisfaction in ranking prediction for personalized cloud service selection. Decis Support Syst 93:1–10. https://doi.org/10.1016/j.dss.2016.09.001

    Article  Google Scholar 

  12. 12.

    Ahlgren P, Jarneving B, Rousseau R (2003) Requirements for a cocitation similarity measure, with special reference to Pearson’s correlation coefficient. J Am Soc Inf Sci Technol 54:550–560. https://doi.org/10.1002/asi.10242

    Article  Google Scholar 

  13. 13.

    Adomavicius G, Zhang J (2016) Classification, ranking, and Top-K stability of recommendation algorithms. Informs J Comput 28:129–147. https://doi.org/10.1287/ijoc.2015.0662

    MathSciNet  Article  Google Scholar 

  14. 14.

    Liu DR, Chen KY, Chou YC, Lee JH (2018) Online recommendations based on dynamic adjustment of recommendation lists. Knowl Based Syst 161:375–389. https://doi.org/10.1016/j.knosys.2018.07.038

    Article  Google Scholar 

  15. 15.

    Xiang L (2011) Research on key technologies of dynamic recommendation system. Bei Jing:Institute of Automation, Chinese Academy of Science

  16. 16.

    Liu B, Wu Y, Gong NZ, et al. (2016) Structural analysis of user choices for mobile App recommendation. Acm Trans Knowl Discov Data 11:17. https://doi.org/10.1145/2983533

    Article  Google Scholar 

  17. 17.

    Rashid AM, Lam SK, Karypis G et al (2006) ClustKNN: a highly scalable hybrid model-memory-based CF algorithm. The Workshop on in Proc of Webkdd

  18. 18.

    Elkahky AM, Song Y, He X (2015) A multi-view deep learning approach for cross domain user modeling in recommendation systems. In: The 24th International conference on world wide web, pp 278–288. https://doi.org/10.1145/2736277.2741667

  19. 19.

    Wang H, Wang N, Yeung DY (2015) Collaborative deep learning for recommender systems. In: The 21th ACM SIGKDD International conference on knowledge discovery and data, pp 1235–1244. https://doi.org/10.1145/2783258.2783273?

  20. 20.

    Koren Y (2008) Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: The 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 426–434. https://doi.org/10.1145/1401890.1401944?

  21. 21.

    Ahn HJ (2008) A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. Inform Sci 178:37–51. https://doi.org/10.1016/j.ins.2007.07.024?

    Article  Google Scholar 

  22. 22.

    Liu H, Hu Z, Mian A, et al. (2014) A new user similarity model to improve the accuracy of collaborative filtering. Knowl Based Syst 56:156–166. https://doi.org/10.1016/j.knosys.2013.11.006

    Article  Google Scholar 

  23. 23.

    Li S, Kawale J, Fu Y (2015) Deep collaborative filtering via marginalized denoising auto-encoder. In: The 24th ACM international on conference on information and knowledge management, pp 811–820. https://doi.org/10.1145/2806416.2806527?

  24. 24.

    Wu Y, DuBois C, Zheng AX, et al. (2016) Collaborative denoising Auto-Encoders for Top-N recommender systems. In: The Ninth ACM international conference on web search and data mining, pp 153–162. https://doi.org/10.1145/2835776.2835837?

  25. 25.

    Strub F, Mary J, Gaudel R (2016) Hybrid recommender system based on autoencoders. In: The 1st workshop on deep learning for recommender systems, pp 11–16. https://doi.org/10.1145/2988450.2988456?

  26. 26.

    Wang X, Lu W, Ester M, et al. (2016) Socialrecommendationwithstrongandweakties. In: The25thACMInternationalonconferenceoninformationandknowledgemanagement,pp5–14.https://doi.org/10.1145/2983323.2983701?

  27. 27.

    Vuurens JBP, Larson M, DeVries AP (2016) Exploringdeepspace:Learningpersonalizedrankinginasemanticspace. In: The1stworkshopondeeplearningforrecommendersystems, pp23–28https://doi.org/10.1145/2988450.2988457

  28. 28.

    Adomavicius G, Kwon YO (2012) Improvingaggregaterecommendationdiversityusingranking-basedtechniques. IEEETransKnowlDataEng 24:896–911. https://doi.org/10.1109/tkde.2011.15?

    Google Scholar 

  29. 29.

    Herlocker JL, Konstan JA, Terveen LG, Riedl JT (2004) Evaluatingcollaborativefilteringrecommendersystems. AcmTransInfSyst 22:5–53. https://doi.org/10.1145/963770.963772

    Google Scholar 

  30. 30.

    Luo X, Zhou M, Xia Y, Zhu Q (2014) Anefficientnon-negativematrix-factorization-basedapproachtocollaborativefilteringforrecommendersystems. IEEETransIndustrInform 10:1273–1284. https://doi.org/10.1109/tii.2014.2308433?

    Google Scholar 

  31. 31.

    Li D, Lv Q, Shang L, Gu N (2017) Efficientprivacy-preservingcontentrecommendationforonlinesocialcommunities. Neurocomputing 219:440–454. https://doi.org/10.1016/j.neucom.2016.09.059

    Article  Google Scholar 

  32. 32.

    Pan YC, Wu DS, Olson DL (2017) Onlinetooffline(O2O)servicerecommendationmethodbasedonmulti-dimensionalsimilaritymeasurement. DecisSupportSyst 103:1–8. https://doi.org/10.1016/j.dss.2017.08.003

    Google Scholar 

Download references

Acknowledgements

This research is partially supported by the Chinese National Natural Science Fund(No. 61841602), the Natural Science Foundation of Shandong Provice (No. ZR2018PF005) and Shandong Province International Cooperation Trianing Project for University Teacher. We express our thanks to Dr. Rongju Li who checked our manuscript.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kai Zheng.

Additional information

Publisher’sNote

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sun, F., Zhuang, H., Xu, S. et al. A Time-aware Hybrid Algorithm for Online Recommendation Services. Mobile Netw Appl (2021). https://doi.org/10.1007/s11036-021-01792-8

Download citation

Keywords

  • Time-aware
  • Stability of interest
  • Cloud computing
  • Popularity of item
  • Popularity bias