Browse > Article
http://dx.doi.org/10.3745/JIPS.01.0069

Personalized Product Recommendation Method for Analyzing User Behavior Using DeepFM  

Xu, Jianqiang (School of Information Science and Engineering, East China University of Science and Technology)
Hu, Zhujiao (School of Microelectronics, Fudan University)
Zou, Junzhong (School of Information Science and Engineering, East China University of Science and Technology)
Publication Information
Journal of Information Processing Systems / v.17, no.2, 2021 , pp. 369-384 More about this Journal
Abstract
In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.
Keywords
DeepFM; Higher-Order Feature; Hit Rate Prediction; K-Means Similarity Clustering; Low-Order Features; Personalized Product Recommendation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 A. Taneja and A. Arora, "Cross domain recommendation using multidimensional tensor factorization," Expert Systems with Applications, vol. 92, pp. 304-316, 2018   DOI
2 L. Yu, L. Liu, and X. Li, "A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce," Expert Systems with Applications, vol. 28, no. 1, pp. 67-77, 2005.   DOI
3 J. Gao, "Research on goods recommendation strategy based on decision tree," Applied Mechanics and Materials, vol. 687, pp. 2718-2721, 2014.   DOI
4 M. Li and L. Hou, "Welfare effects of network neutrality in mobile Internet market," Enterprise Information Systems, vol. 14, no. 3, pp. 352-367, 2020.   DOI
5 D. Hidalgo-Mazzei, V. L. Nikolova, S. Kitchen, and A. H. Young, "Internet-connected devices ownership, use and interests in bipolar disorder: from desktop to mobile mental health," Digital Psychiatry, vol. 2, no. 1, pp. 1-7, 2019.   DOI
6 C. B. Jiang, I. H. Liu, Y. N. Chung, and J. S. Li, "Novel intrusion prediction mechanism based on honeypot log similarity," International Journal of Network Management, vol. 26, no. 3, pp. 156-175, 2016.   DOI
7 Y. H. Li, Z. P. Fan, and G. H. Qiao, "Product recommendation incorporating the consideration of product performance and customer service factors," Kybernetes, vol. 46, no. 10, pp. 1753-1776, 2017.   DOI
8 X. Lai, L. He, and Q. Zhou, "Personalized product service recommendation based on user portrait mathematical model," in Proceedings of 2018 International Symposium on Communication Engineering & Computer Science (CECS), Hohhot, China, 2018, pp. 328-333.
9 I. Baako, S. Umar, and P. Gidisu, "Privacy and security concerns in electronic commerce websites in Ghana: a survey study," International Journal of Computer Network and Information Security, vol. 11, no. 10, pp. 19-25, 2019.   DOI
10 C. Burgos, J. C. Cortes, I. C. Lombana, D. Martinez-Rodriguez, and R. J. Villanueva, "Modeling the dynamics of the frequent users of electronic commerce in Spain using optimization techniques for inverse problems with uncertainty," Journal of Optimization Theory and Applications, vol. 182, no. 2, pp. 785-796, 2019.   DOI
11 N. Dridi and M. Hadzagic, "Akaike and Bayesian information criteria for hidden Markov models," IEEE Signal Processing Letters, vol. 26, no. 2, pp. 302-306, 2019.   DOI
12 J. P. McCrae and P. Buitelaar, "Linking datasets using semantic textual similarity," Cybernetics and Information Technologies, vol. 18, no. 1, pp. 109-123, 2018.   DOI
13 X. Kang and X. Deng, "An improved modified Cholesky decomposition approach for precision matrix estimation," Journal of Statistical Computation and Simulation, vol. 90, no. 3, pp. 443-464, 2020.   DOI
14 M. Yavari and A. Nazemi, "Fractional infinite-horizon optimal control problems with a feed forward neural network scheme," Network: Computation in Neural Systems, vol. 30, no. 1-4, pp. 125-147, 2019.   DOI
15 Z. Wang, M. Wan, X. Cui, L. Liu, Z. Liu, W. Xu, and L. He, "Personalized recommendation algorithm based on product reviews," Journal of Electronic Commerce in Organizations, vol. 16, no. 3, pp. 22-38, 2018.   DOI
16 J. Wu and Z. Wu, "Improved fuzzy C-means clustering for personalized product recommendation," Research Journal of Applied Sciences, Engineering and Technology, vol. 6, no. 3, pp. 393-399, 2013.   DOI
17 Y. Ning, L. Liu, and Z. Xu, "Research on personalized recommendation algorithm based on user model and user-project matrix," in Proceedings of 2011 International Conference on Computer Science and Network Technology, Harbin, China, 2011, pp. 2400-2402.
18 Y. Guo, M. Wang, and X. Li, "An interactive personalized recommendation system using the hybrid algorithm model," Symmetry, vol. 9, no. 10, article no. 216, 2017. https://doi.org/10.3390/sym9100216   DOI
19 V. S. Dixit, S. Gupta, and P. Jain, "A propound hybrid approach for personalized online product recommendations," Applied Artificial Intelligence, vol. 32, no. 9-10, pp. 785-801, 2018.   DOI
20 L. Luo, H. Xie, Y. Rao, and F. L. Wang, "Personalized recommendation by matrix co-factorization with tags and time information," Expert Systems with Applications, vol. 119, pp. 311-321, 2019.   DOI
21 B. Pang, M. Yang, and C. Wang, "A novel top-n recommendation approach based on conditional variational auto-encoder," Advances in Knowledge Discovery and Data Mining. Cham, Switzerland: Springer, 2019, pp. 357-368.
22 S. T. Cheng, C. L. Chou, and G. J. Horng, "The adaptive ontology-based personalized recommender system," Wireless Personal Communications, vol. 72, no. 4, pp. 1801-1826, 2013.   DOI
23 S. Zhang, C. Zhao, and F. Gao, "Incipient fault detection for multiphase batch processes with limited batches," IEEE Transactions on Control Systems Technology, vol. 27, no. 1, pp. 103-117, 2017.   DOI
24 L. Zhang, J. Li, Q. Zhang, F. Meng, and W. Teng, "Domain knowledge-based link prediction in customerproduct bipartite graph for product recommendation," International Journal of Information Technology & Decision Making, vol. 18, no. 1, pp. 311-338, 2019.   DOI
25 M. Hao and B. Q. Zhang, "Study on recommendation method based on product evaluation concept tree and collaborative filtering algorithm," Applied Mechanics and Materials, vol. 519, pp. 401-404, 2014.   DOI
26 M. Mpinganjira and D. K. Maduku, "Ethics of mobile behavioral advertising: antecedents and outcomes of perceived ethical value of advertised brands," Journal of Business Research, vol. 95, pp. 464-478, 2019.   DOI
27 M. S. Islam and S. A. Eva, "Electronic commerce toward digital Bangladesh: business expansion model based on value chain in the network economy," Studies in Business & Economics, vol. 14, no. 1, pp. 87-98, 2019.   DOI
28 W. Hong, L. Li, and T. Li, "Product recommendation with temporal dynamics," Expert Systems with Applications, vol. 39, no. 16, pp. 12398-12406, 2012.   DOI
29 Y. Cui, L. Zhang, Q. Wang, P. Chen, and C. Xie, "Heterogeneous network linkage-weight based link prediction in bipartite graph for personalized recommendation," Procedia Computer Science, vol. 91, pp. 953-958, 2016.   DOI
30 Y. Huang, N. N. Wang, H. Zhang, and J. Wang, "A novel product recommendation model consolidating price, trust and online reviews," Kybernetes, vol. 48, no. 6, pp. 1355-1372, 2019.   DOI