Skip to main content
SpringerLink
Log in

A disaggregated interest-extraction network for click-through rate prediction

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Click-through rate (CTR) prediction is of crucial significance to computational advertising and recommendation systems. In recent years, deep learning has shown great potential in personalized recommendation. However, existing studies ignored the multi-objective nature of users’ click behaviors, i.e., that users tend to buy more than one item at the same time. In spite of the fact that user rating data can be used to make up for missing information among items, particularly items that share the same tags, the existing deep models for recommendation fail to exploit user ratings and do not reflect user interests adequately. To address this problem, we propose a CTR prediction model named the Disaggregated Interest-Extraction Network (Di-Net) to disaggregate a user’s click-through sequence into three sub-sequences, namely the basic feature sub-sequence, the consistent feature sub-sequence, and the correlated feature sub-sequence. Di-Net uses a Gated Recurrent Unit with a user-item rating update gate (URGRU) to extract sufficient multiple-layer features hidden behind user ratings. The experimental results on two public datasets (Amozon product dataset and MovieLens dataset) show that Di-Net outperforms the state-of-the-art models, such as DIEN and AutoInt. The AUCs of Di-Net on Books subset of Amozon, Clothing, Shoes, and Jewelry subset of Amozon and MovieLens dataset reach 0.8523, 0.7421 and 0.8612, respectively. Additional experiments show that the use of disaggregated sequences supports the modeling of user interests adequately.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. In: Proc. 3rd Int. Conf. Learn. Represent., pp. 1–15

  2. Chapelle O, Manavoglu E, Rosales R (2015) Simple and scalable response prediction for display advertising. ACM Trans Intell Syst Technol 5(4):1–34

    Article  Google Scholar 

  3. Chen Y, Kapralov M, Pavlov D, Canny J (2009) Factor modeling for advertisement targeting. In NIPS, 324–332

  4. Chen T, Yin H, Nguyen QVH, Peng W-C, Li X, Zhou X (2019) Sequence aware factorization machines for temporal predictive analytics. arXiv preprint arXiv:1911.02752

  5. Chen S, Yan G, Zhang W, Ji J, Jiang R, Lin Z (2021) RA3 is a reference-guided approach for epigenetic characterization of single cells. Nat Commun 12(2177):2021

    Google Scholar 

  6. Chen X, Chen S, Song S, Gao Z, Hou L, Zhang X, Lv H, Jiang R (2022) Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding. Nat Mach Intell 4(116–126):2022–2126

    Google Scholar 

  7. Cheng H-T, Koc L, Harmsen J, Shaked T, Chandra T, Aradhye H, …, Shah H (2016) Wide & deep learning for recommender systems. In: Proc. 1st workshop deep learn. Recommender Syst, pp. 7-10

  8. Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555

  9. Covington, P, Adams, J, Sargin, E (2016) Deep neural networks for youtube recommendations. In: Proceedings of the 10th ACM conference on recommender Systems.ACM,191–198

  10. Graves, A, Mohamed, A, Hinton, G (2013) Speech recognition with deep recurrent neural networks. In: Proc. IEEE Int. Conf. Acoust., speech Signal Process., pp. 6645–6649

  11. Guo H, Tang R, Ye Y, Li Z, He X (2017) DeepFM: a factorization machine based neural network for CTR prediction. In: Proc. 26th Int. joint Conf. Artif. Intell. pp. 1725–1731

  12. Harper FM, Konstan JA (2015) The MovieLens Datasets: History and Context. ACM Trans Interact Intell Syst 5:1–19

    Article  Google Scholar 

  13. He X, Pan J, Jin O, Xu T, Liu B, Xu T, Candela J (2014) Practical lessons from predicting clicks on ads at Facebook. In: Proc. 8th Int. workshop data mining online advertising, New York, NY, USA, pp. 1-9

  14. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  15. Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc. 30th IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 2261-2269

  16. Jaiswal S, Virmani S, Sethi V, De K, Roy PP (2018) An intelligent recommendation system using gaze and emotion detection. Multimed Tools Appl 78(11):14231–14250

    Article  Google Scholar 

  17. Juan Y, Zhuang Y, Chin WS, Lin CJ (2016) Field-aware factorization machines for CTR prediction. In: Proceedings of the 10th ACM conference on recommender systems. ACM, 43-50

  18. Juan Y, Lefortier D, Chapelle O (2017) Field-aware factorization machines in a real-world online advertising system. In: Proceedings of the 26th international conference on world wide web companion. International world wide web conferences steering committee, 680–688

  19. Khurana V, Gahalawat M, Kumar P, Roy PP, Soleymani M (2021) A survey on Neuromarketing using EEG signals. IEEE Trans Cogni Deve Syst 13:732–749

    Article  Google Scholar 

  20. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proc. Int. Conf. Learn. Represent., pp. 1–15

  21. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1097–1105

  22. Kumar S, De K, Roy PP (2020) Movie recommendation system using sentiment analysis from microblogging data. IEEE Trans Comput Soc Syst 7(4):915–923

    Article  Google Scholar 

  23. Li Z, Cheng W, Chen Y, Chen H, Wang W (2020) Interpretable click-through rate prediction through hierarchical attention. WSDM ‘20: the thirteenth ACM international conference on web search and data mining. ACM

  24. Lian J, Zhou X, Zhang F, Chen Z, Xie X, Sun G (2018) XDeepFM: combining explicit and implicit feature interactions for recommender systems. In: Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery data mining, pp. 1754–1763

  25. Liu Q, Chen S, Jiang R, Wong WH (2021) Simultaneous deep generative modeling and clustering of single cell genomic data. Nat Mach Intell 3(536–544):2021–2544

    Google Scholar 

  26. Liu Q, Xu J, Jiang R, Wong WH (2021) Density estimation using deep generative neural networks. Proc Natl Acad Sci U S A 118(15):e2101344118

    Article  MathSciNet  Google Scholar 

  27. Lyu Z, Dong Y, Huo C, Ren W (2020) Deep match to rank model for personalized click-through rate prediction. Proc AAAI Conf Artif Intell 34(1):156–163

    Google Scholar 

  28. Mcauley J, Targett C, Shi Q, Hengel AVD (2015) Image-based recommendations on styles and substitutes. ACM

  29. Pan J, Xu J, Ruiz AL, Zhao W, Pan S, Sun Y, Lu Q (2018) Field-weighted factorization Machines for Click-through Rate Prediction in display advertising. In: Proceedings of the 2018 world wide web conference on world wide web. International world wide web conferences steering committee, 1349–1357

  30. Pi Q, Bian W, Zhou G, Zhu X, Gai K (2019) Practice on long sequential user behavior modeling for click-through rate prediction. KDD’19

  31. Qu Y, Cai H, Ren K, Zhang W, Yu Y, Wen Y, Wang J (2016) Product based neural networks for user response prediction. In: Proc. IEEE 16th Int. Conf. Data mining (ICDM), pp. 1149–1154

  32. Rendle S (2010) Factorization machines. In: Proceedings of the 10th international conference on data mining, IEEE, 995-1000

  33. Song W, Shi C, Xiao Z, Duan Z, Xu Y, Zhang M, Tang J (2019) AutoInt: automatic feature interaction learning via self-attentive neural networks. In: Proc. 28th ACM Int. Conf. Inf. Knowl. Manage. (CIKM), pp. 1161–1170

  34. Ta A-P (2015) Factorization machines with follow-the-regularized-leader for CTR prediction in display advertising. In: Proc. IEEE Int. Conf. Big data (big data), pp. 2889-2891

  35. Tao Z, Wang X, He X, Huang X, Chua T (2019) HoAFM: a high-order attentive factorization machine for CTR prediction. Inf Process Manag 57:102076. https://doi.org/10.1016/j.ipm.2019.102076

    Article  Google Scholar 

  36. Trofimov I, Kornetova A, Topinskiy V (2012) Using boosted trees for click-through rate prediction for sponsored search. ADKDD, pp 2:1–2:6

  37. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017). Attention is all you need. In: Proc. 31st Int. Conf. Neural Inf. Process. Syst. Red hook, NY, USA: Curran associates

  38. Wang R, Fu B, Fu G, Wang M (2017). Deep & cross network for ad click predictions. In: Proc. ADKDD, pp. 1–7

  39. Xiao J, Ye H, He X, Zhang H, Wu F, Chua T-S (2017) Attentional factorization machines: learning the weight of feature interactions via attention networks. In: Proc. 26th Int. joint Conf. Artif. Intell., pp. 1–7.

  40. Xie R, Ling C, Wang Y, Wang R, Lin L (2020) Deep feedback network for recommendation. Twenty-ninth international joint conference on artificial intelligence and seventeenth Pacific rim international conference on artificial intelligence (IJCAI-PRICAI-20)

  41. Zhai S, Chang K-H, Zhang R, Zhang ZM (2016) DeepIntent: learning attentions for online advertising with recurrent neural networks. In: Proc. ACM SIGKDD Int. Conf. Knowl. Discovery data mining, pp. 1295–1304

  42. Zhou G, Zhu X, Song C, Fan Y, Zhu H, Ma X, Gai K (2018) Deep interest network for click-through rate prediction. In: Proceedings of the 24th ACM SIGKDD international conference on Knowledge Discovery & Data Mining, ACM, 1059-1068

  43. Zhou C, Bai J, Song J, Liu X, Zhao Z, Chen X, Gao J (2018) ATRank: an attention-based user behavior modeling framework for recommendation. In: Proc. 32nd AAAI Conf. Artif. Intell

  44. Zhou G, Mou N, Fan Y, Pi Q, Bian W, Zhou C, Zhu X, Gai K (2019) Deep interest evolution network for click-through rate prediction. Proc AAAI Conf Artif Intell 33:5941–5948

    Google Scholar 

Download references

Acknowledgements

This work was partly funded by the National Natural Science Foundation of China (Nos. 72271024, 71871019, 71729001).

Author information

Authors and Affiliations

  1. School of Economics and Management, University of Science and Technology Beijing, Beijing, 100083, China

    Mingxin Gan, Danyang Li & Xiongtao Zhang

Authors
  1. Mingxin Gan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Danyang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiongtao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mingxin Gan.

Ethics declarations

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Conflict of interest

Author Mingxin Gan declares that she has no conflict of interest. Author Danyang Li declares that she has no conflict of interest. Author Xiongtao Zhang declares that he has no conflict of interest.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gan, M., Li, D. & Zhang, X. A disaggregated interest-extraction network for click-through rate prediction. Multimed Tools Appl 82, 27771–27793 (2023). https://doi.org/10.1007/s11042-023-14584-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-14584-x

Keywords

Search

Navigation