Research on the Design of E-commerce Recommendation System


Daniel Yang,Deakin University, Australia
Saman Grice*,Deakin University, Australia


In recent years, the amount of data in various fields, especially in the e-commerce industry, has continued to rise, which is inseparable from the rapid development of information technology and the application of massive data processing technology. To use massive amounts of data to serve users, and to promote user retention, the use of recommendation systems is very important. Based on a hybrid recommendation idea, this paper designs an e-commerce recommendation system based on big data technology. First, the system needs analysis, and the overall architecture of the system is designed. Then the design process of each recommended module is explained in detail. This article combines demographic-based recommendation algorithm, content-based recommendation algorithm, ALS-based collaborative filtering recommendation algorithm, and model-based real-time recommendation algorithm to form a hybrid recommendation module to provide users with recommendation services. Among them, the demographic-based recommendation can solve the user's cold start problem, the collaborative filtering recommendation does not require the content attributes of the item to be recommended, and the model-based recommendation algorithm can provide users with real-time recommendation services.



E-commerce, Recommendation system, Recommendation algorithm, Collaborative filtering


[1] D. Goldberg, et. al., “Using collaborative filtering to weave an information tapestry,” Communications of the Acm, (1992)
[2] P. Pu, L. Chen, and P. Kumar, “Evaluating product search and recommender systems for E-commerce environments,” Electronic Commerce Research, vol.8, no.1-2, pp.1-27, (2008)
[3] B. N. Miller, I. Albert, and S. K. Lam, “Movie lens unplugged: Experiences with an occasionally connected recommender system,” International Conference on Intelligent User Interfaces, (AN), pp.263-266, (2003)
[4] P. Resnick and H. R. Varian, “Recommender systems. Commun ACM,” Communications of the ACM, vol.40, no.3, pp.56-58, (1997)
[5] C. A. Gomez-Uribe and N. Hunt, “The netflix recommender system: Algorithms, business value, and innovation,” Acm Transactions on Management Information Systems, (2016)
[6] S. Ghemawat, H, Gobioff, and S. T. Leung, “The google file system,” ACM SIGOPS Operating Systems Review, ACM, (2003), vol.37, no.5, pp29-43
[7] J. Dean and S. Ghemawat, “MapReduce: Simplified data processing on large clusters,” Sixth Symposium on Operating System Design and Implementation. USENIX Association, (2004)
[8] K. Shvachko, H. Kuang, and S. Radia, “The Hadoop distributed file system,” IEEE Symposium on Mass Storage Systems and Technologies, IEEE, (2010)
[9] D. Xicheng. “Hadoop technology insider-in-depth analysis of YARN architecture design and implementation principles,” Machinery Industry Press, (2013)
[10] S. Narayan, S. Bailey, and A. Daga, “Hadoop acceleration in an open flow-based cluster,” (2013)
[11] N. Bansal, D. Upadhyay, and U. Mittal, “Concurrency control techniques in HDFS,” Confluence the Next Generation Information Technology Summit, IEEE, (2014)
[12] X. Liang, “Recommendation system practice,” People's Posts and Telecommunications Press, (2012)
[13] X. Junluan, S. Saisai, and Spark “Streaming: The newbie of large-scale streaming data processing programmer,” (2014), no.2, pp.44-47
[14] D. Siegal, J. Guo, and G. Agrawal, “Smart-mllib: A high-performance machine-learning library,” IEEE International Conference on Cluster Computing (CLUSTER), IEEE, (2016)
[15] H. Li, A. Ghodsi, and S. Shenker, “Tachyon: Reliable, memory speed storage for cluster computing frameworks,” (2014)
[16] R. He and J. Mcauley, “Ups and downs: Modeling the visual evolution of fashion trends with one-class Collaborative filtering,” (2016)
[17] R. Ronen, N. Koenigstein, and E. Ziklik, Press the 7th ACM conference - Hong Kong, China (2013.10.12-2013.10.16) Proceedings of the 7th ACM conference on Recommender systems - RecSys 13 - Selecting content-based features for collaborative filtering recommenders, pp.407-410, (2013)
[18] C. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Climate Research, vol.30, no.1, pp.79-82, (2005)
[19] D. M. Powers, “Evaluation: From precision, recall and f-measure to ROC, informedness, markedness and correlation,” (2011)


  • APA:
    Yang,D.& Grice*,S.(2018). Research on the Design of E-commerce Recommendation System. International Journal of Smart Business and Technology, 6(1), 15-30. 10.21742/IJSBT.2018.6.1.02
  • Harvard:
    Yang,D., Grice*,S.(2018). "Research on the Design of E-commerce Recommendation System". International Journal of Smart Business and Technology, 6(1), pp.15-30. doi:10.21742/IJSBT.2018.6.1.02
  • IEEE:
    [1] D.Yang, S.Grice*, "Research on the Design of E-commerce Recommendation System". International Journal of Smart Business and Technology, vol.6, no.1, pp.15-30, Jun. 2018
  • MLA:
    Yang Daniel and Grice* Saman. "Research on the Design of E-commerce Recommendation System". International Journal of Smart Business and Technology, vol.6, no.1, Jun. 2018, pp.15-30, doi:10.21742/IJSBT.2018.6.1.02


  • Volume 6, No. 1, 2018
  • ISSN(p):2288-8969
  • ISSN(e):2207-516X
  • Published:Jun. 2018