Personalized Product Recommendation Method for Analyzing User Behavior Using DeepFM = Personalized Product Recommendation Method for Analyzing User Behavior Using DeepFM

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 M. Li, "Welfare effects of network neutrality in mobile Internet market" 14 (14): 352-367, 2020

2 S. T. Cheng, "The adaptive ontology-based personalized recommender system" 72 (72): 1801-1826, 2013

3 M. Hao, "Study on recommendation method based on product evaluation concept tree and collaborative filtering algorithm" 519 : 401-404, 2014

4 Y. Ning, "Research on personalized recommendation algorithm based on user model and user-project matrix" 2400-2402, 2011

5 J. Gao, "Research on goods recommendation strategy based on decision tree" 687 : 2718-2721, 2014

6 W. Hong, "Product recommendation with temporal dynamics" 39 (39): 12398-12406, 2012

7 Y. H. Li, "Product recommendation incorporating the consideration of product performance and customer service factors" 46 (46): 1753-1776, 2017

8 I. Baako, "Privacy and security concerns in electronic commerce websites in Ghana : a survey study" 11 (11): 19-25, 2019

9 L. Luo, "Personalized recommendation by matrix co-factorization with tags and time information" 119 : 311-321, 2019

10 Z. Wang, "Personalized recommendation algorithm based on product reviews" 16 (16): 22-38, 2018

11 X. Lai, "Personalized product service recommendation based on user portrait mathematical model" 328-333, 2018

12 C. B. Jiang, "Novel intrusion prediction mechanism based on honeypot log similarity" 26 (26): 156-175, 2016

13 C. Burgos, "Modeling the dynamics of the frequent users of electronic commerce in Spain using optimization techniques for inverse problems with uncertainty" 182 (182): 785-796, 2019

14 J. P. McCrae, "Linking datasets using semantic textual similarity" 18 (18): 109-123, 2018

15 D. Hidalgo-Mazzei, "Internet-connected devices ownership, use and interests in bipolar disorder : from desktop to mobile mental health" 2 (2): 1-7, 2019

16 S. Zhang, "Incipient fault detection for multiphase batch processes with limited batches" 27 (27): 103-117, 2017

17 J. Wu, "Improved fuzzy C-means clustering for personalized product recommendation" 6 (6): 393-399, 2013

18 Y. Cui, "Heterogeneous network linkage-weight based link prediction in bipartite graph for personalized recommendation" 91 : 953-958, 2016

19 M. Yavari, "Fractional infinite-horizon optimal control problems with a feed forward neural network scheme" 30 (30): 125-147, 2019

20 M. Mpinganjira, "Ethics of mobile behavioral advertising : antecedents and outcomes of perceived ethical value of advertised brands" 95 : 464-478, 2019

21 M. S. Islam, "Electronic commerce toward digital Bangladesh : business expansion model based on value chain in the network economy" 14 (14): 87-98, 2019

22 L. Zhang, "Domain knowledge-based link prediction in customerproduct bipartite graph for product recommendation" 18 (18): 311-338, 2019

23 A. Taneja, "Cross domain recommendation using multidimensional tensor factorization" 92 : 304-316, 2018

24 Y. Guo, "An interactive personalized recommendation system using the hybrid algorithm model" 9 (9): 2017

25 X. Kang, "An improved modified Cholesky decomposition approach for precision matrix estimation" 90 (90): 443-464, 2020

26 N. Dridi, "Akaike and Bayesian information criteria for hidden Markov models" 26 (26): 302-306, 2019

27 B. Pang, "Advances in Knowledge Discovery and Data Mining" Springer 357-368, 2019

28 V. S. Dixit, "A propound hybrid approach for personalized online product recommendations" 32 (32): 785-801, 2018

29 Y. Huang, "A novel product recommendation model consolidating price, trust and online reviews" 48 (48): 1355-1372, 2019

30 L. Yu, "A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce" 28 (28): 67-77, 2005