A Practical Deep Online Ranking System in E-commerce Recommendation

  • Yan YanEmail author
  • Zitao Liu
  • Meng Zhao
  • Wentao Guo
  • Weipeng P. Yan
  • Yongjun Bao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11053)


User online shopping experience in modern e-commerce websites critically relies on real-time personalized recommendations. However, building a productionized recommender system still remains challenging due to a massive collection of items, a huge number of online users, and requirements for recommendations to be responsive to user actions. In this work, we present our relevant, responsive, and scalable deep online ranking system (DORS) that we developed and deployed in our company. DORS is implemented in a three-level architecture which includes (1) candidate retrieval that retrieves a board set of candidates with various business rules enforced; (2) deep neural network ranking model that takes advantage of available user and item specific features and their interactions; (3) multi-arm bandits based online re-ranking that dynamically takes user real-time feedback and re-ranks the final recommended items in scale. Given a user as a query, DORS is able to precisely capture users’ real-time purchasing intents and help users reach to product purchases. Both offline and online experimental results show that DORS provides more personalized online ranking results and makes more revenue.


Recommender system E-commerce Deep learning Multi-arm bandits 

Supplementary material

473908_1_En_12_MOESM1_ESM.pdf (308 kb)
Supplementary material 1 (pdf 307 KB)


  1. 1.
    Agarwal, D., Chen, B.C., Elango, P.: Fast online learning through offline initialization for time-sensitive recommendation. In: KDD, pp. 703–712. ACM (2010)Google Scholar
  2. 2.
    Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2–3), 235–256 (2002)CrossRefGoogle Scholar
  3. 3.
    Basak, D., Pal, S., Patranabis, D.C.: Support vector regression. Neural Inf. Process.-Lett. Rev. 11(10), 203–224 (2007)Google Scholar
  4. 4.
    Burges, C., et al.: Learning to rank using gradient descent. In: ICML, pp. 89–96. ACM (2005)Google Scholar
  5. 5.
    Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: from pairwise approach to listwise approach. In: ICML, pp. 129–136. ACM (2007)Google Scholar
  6. 6.
    Chang, S., et al.: Streaming recommender systems. In: WWW, pp. 381–389 (2017)Google Scholar
  7. 7.
    Chen, C., Yin, H., Yao, J., Cui, B.: TeRec: a temporal recommender system over tweet stream. VLDB 6(12), 1254–1257 (2013)Google Scholar
  8. 8.
    Cherkassky, V., Ma, Y.: Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw. 17(1), 113–126 (2004)CrossRefGoogle Scholar
  9. 9.
    Davidson, J., et al.: The YouTube video recommendation system. In: RecSys, pp. 293–296. ACM (2010)Google Scholar
  10. 10.
    Diaz-Aviles, E., Drumond, L., Schmidt-Thieme, L., Nejdl, W.: Real-time top-n recommendation in social streams. In: RecSys, pp. 59–66. ACM (2012)Google Scholar
  11. 11.
    Ding, Y., Li, X.: Time weight collaborative filtering. In: CIKM, pp. 485–492. ACM (2005)Google Scholar
  12. 12.
    Gao, H., Tang, J., Hu, X., Liu, H.: Exploring temporal effects for location recommendation on location-based social networks. In: RecSys, pp. 93–100. ACM (2013)Google Scholar
  13. 13.
    Gomez-Uribe, C.A., Hunt, N.: The Netflix recommender system: algorithms, business value, and innovation. TMIS 6(4), 13 (2016)Google Scholar
  14. 14.
    Guan, Z., Bu, J., Mei, Q., Chen, C., Wang, C.: Personalized tag recommendation using graph-based ranking on multi-type interrelated objects. In: SIGIR, pp. 540–547. ACM (2009)Google Scholar
  15. 15.
    Gultekin, S., Paisley, J.: A collaborative Kalman filter for time-evolving dyadic processes. In: ICDM, pp. 140–149. IEEE (2014)Google Scholar
  16. 16.
    Hannon, J., Bennett, M., Smyth, B.: Recommending Twitter users to follow using content and collaborative filtering approaches. In: RecSys, pp. 199–206. ACM (2010)Google Scholar
  17. 17.
    Koren, Y.: Collaborative filtering with temporal dynamics. Commun. ACM 53(4), 89–97 (2010)CrossRefGoogle Scholar
  18. 18.
    Lang, K.: NewsWeeder: learning to filter netnews. In: Proceedings of the 12th International Machine Learning Conference (ML 1995) (1995)CrossRefGoogle Scholar
  19. 19.
    Langford, J., Zhang, T.: The epoch-greedy algorithm for multi-armed bandits with side information. In: NIPS, pp. 817–824 (2008)Google Scholar
  20. 20.
    Liu, Y., Miao, J., Zhang, M., Ma, S., Ru, L.: How do users describe their information need: query recommendation based on snippet click model. Expert Syst. Appl. 38(11), 13847–13856 (2011)Google Scholar
  21. 21.
    Lu, D., et al.: Cross-media event extraction and recommendation. In: NAACL, pp. 72–76 (2016)Google Scholar
  22. 22.
    Lu, Z., Agarwal, D., Dhillon, I.S.: A spatio-temporal approach to collaborative filtering. In: RecSys, pp. 13–20. ACM (2009)Google Scholar
  23. 23.
    Rendle, S.: Factorization machines. In: ICDM, pp. 995–1000. IEEE (2010)Google Scholar
  24. 24.
    Rendle, S., Freudenthaler, C., Schmidt-Thieme, L.: Factorizing personalized Markov chains for next-basket recommendation. In: WWW, pp. 811–820. ACM (2010)Google Scholar
  25. 25.
    Rendle, S., Schmidt-Thieme, L.: Online-updating regularized kernel matrix factorization models for large-scale recommender systems. In: RecSys, pp. 251–258. ACM (2008)Google Scholar
  26. 26.
    Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: WWW, pp. 285–295. ACM (2001)Google Scholar
  27. 27.
    Severyn, A., Moschitti, A.: Learning to rank short text pairs with convolutional deep neural networks. In: SIGIR, pp. 373–382. ACM (2015)Google Scholar
  28. 28.
    Tang, J., Hu, X., Gao, H., Liu, H.: Exploiting local and global social context for recommendation. In: IJCAI, vol. 13, pp. 2712–2718 (2013)Google Scholar
  29. 29.
    Tang, J., Hu, X., Liu, H.: Social recommendation: a review. Soc. Netw. Anal. Min. 3(4), 1113–1133 (2013)CrossRefGoogle Scholar
  30. 30.
    Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3/4), 285–294 (1933)CrossRefGoogle Scholar
  31. 31.
    Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge, England (1989)Google Scholar
  32. 32.
    Xiang, L., et al.: Temporal recommendation on graphs via long-and short-term preference fusion. In: KDD, pp. 723–732. ACM (2010)Google Scholar
  33. 33.
    Xiong, L., Chen, X., Huang, T.K., Schneider, J., Carbonell, J.G.: Temporal collaborative filtering with bayesian probabilistic tensor factorization. In: SDM. pp. 211–222. SIAM (2010)Google Scholar
  34. 34.
    Yin, D., Hong, L., Xue, Z., Davison, B.D.: Temporal dynamics of user interests in tagging systems. In: AAAI (2011)Google Scholar
  35. 35.
    Yu, X., et al.: Personalized entity recommendation: A heterogeneous information network approach. In: WSDM. pp. 283–292. ACM (2014)Google Scholar
  36. 36.
    Zhang, Y., Zhang, M., Liu, Y., Ma, S., Feng, S.: Localized matrix factorization for recommendation based on matrix block diagonal forms. In: WWW (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yan Yan
    • 1
    Email author
  • Zitao Liu
    • 2
  • Meng Zhao
    • 1
  • Wentao Guo
    • 1
  • Weipeng P. Yan
    • 1
  • Yongjun Bao
    • 1
  1. 1.Intelligent Advertising LabJD.COMMountain ViewUSA
  2. 2.TAL AI LabTAL Education GroupBeijingChina

Personalised recommendations