Personalized Product Recommendation Method for Analyzing User Behavior Using DeepFM
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracyof model recommendation will be greatly affected. To solve this problem, a personalized productrecommendation 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 ofsimilarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationshipbetween low- and high-order feature combinations is learned from log data, and the click rate prediction modelis constructed. Finally, based on the predicted click-through rate, products are recommended to users insequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and0.0253, 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 betterrecommendation effect.
Abstract
In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracyof model recommendation will be greatly affected. To solve this problem, a personalized productrecommendation 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 ofsimilarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationshipbetween low- and high-order feature combinations is learned from log data, and the click rate prediction modelis constructed. Finally, based on the predicted click-through rate, products are recommended to users insequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and0.0253, 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 betterrecommendation effect.
참고문헌 (30)
- M. Li, "Welfare effects of network neutrality in mobile Internet market", Enterprise Information Systems, 14(3), pp.352~367 (2020)
- D. Hidalgo-Mazzei, "Internet-connected devices ownership, use and interests in bipolar disorder : from desktop to mobile mental health", Digital Psychiatry, 2(1), pp.1~7 (2019)
- I. Baako, "Privacy and security concerns in electronic commerce websites in Ghana : a survey study", International Journal of Computer Network and Information Security, 11(10), pp.19~25 (2019)
- C. Burgos, "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, 182(2), pp.785~796 (2019)
- Y. Huang, "A novel product recommendation model consolidating price, trust and online reviews", Kybernetes, 48(6), pp.1355~1372 (2019)
- Y. H. Li, "Product recommendation incorporating the consideration of product performance and customer service factors", Kybernetes, 46(10), pp.1753~1776 (2017)
- Y. Cui, "Heterogeneous network linkage-weight based link prediction in bipartite graph for personalized recommendation", Procedia Computer Science, 91, pp.953~958 (2016)
- M. Mpinganjira, "Ethics of mobile behavioral advertising : antecedents and outcomes of perceived ethical value of advertised brands", Journal of Business Research, 95, pp.464~478 (2019)
- M. S. Islam, "Electronic commerce toward digital Bangladesh : business expansion model based on value chain in the network economy", Studies in Business & Economics, 14(1), pp.87~98 (2019)
- N. Dridi, "Akaike and Bayesian information criteria for hidden Markov models", IEEE Signal Processing Letters, 26(2), pp.302~306 (2019)
- Z. Wang, "Personalized recommendation algorithm based on product reviews", Journal of Electronic Commerce in Organizations, 16(3), pp.22~38 (2018)
- J. Wu, "Improved fuzzy C-means clustering for personalized product recommendation", Research Journal of Applied Sciences, Engineering and Technology, 6(3), pp.393~399 (2013)
- Y. Ning, "Research on personalized recommendation algorithm based on user model and user-project matrix", Proceedings of 2011 International Conference on Computer Science and Network Technology, pp.2400~2402 (2011)
- Y. Guo, "An interactive personalized recommendation system using the hybrid algorithm model", Symmetry, 9(10) (2017)[DOI]
- V. S. Dixit, "A propound hybrid approach for personalized online product recommendations", Applied Artificial Intelligence, 32(9-10), pp.785~801 (2018)
- X. Lai, "Personalized product service recommendation based on user portrait mathematical model", Proceedings of 2018 International Symposium on Communication Engineering &Computer Science (CECS), pp.328~333 (2018)
- L. Luo, "Personalized recommendation by matrix co-factorization with tags and time information", Expert Systems with Applications, 119, pp.311~321 (2019)
- B. Pang, "Advances in Knowledge Discovery and Data Mining", pp.357~368 (2019), Springer
- S. T. Cheng, "The adaptive ontology-based personalized recommender system", Wireless Personal Communications, 72(4), pp.1801~1826 (2013)
- W. Hong, "Product recommendation with temporal dynamics", Expert Systems with Applications, 39(16), pp.12398~12406 (2012)
- L. Zhang, "Domain knowledge-based link prediction in customerproduct bipartite graph for product recommendation", International Journal of Information Technology &Decision Making, 18(1), pp.311~338 (2019)
- M. Hao, "Study on recommendation method based on product evaluation concept tree and collaborative filtering algorithm", Applied Mechanics and Materials, 519, pp.401~404 (2014)
- A. Taneja, "Cross domain recommendation using multidimensional tensor factorization", Expert Systems with Applications, 92, pp.304~316 (2018)
- L. Yu, "A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce", Expert Systems with Applications, 28(1), pp.67~77 (2005)
- J. Gao, "Research on goods recommendation strategy based on decision tree", Applied Mechanics and Materials, 687, pp.2718~2721 (2014)
- C. B. Jiang, "Novel intrusion prediction mechanism based on honeypot log similarity", International Journal of Network Management, 26(3), pp.156~175 (2016)
- J. P. McCrae, "Linking datasets using semantic textual similarity", Cybernetics and Information Technologies, 18(1), pp.109~123 (2018)
- X. Kang, "An improved modified Cholesky decomposition approach for precision matrix estimation", Journal of Statistical Computation and Simulation, 90(3), pp.443~464 (2020)
- M. Yavari, "Fractional infinite-horizon optimal control problems with a feed forward neural network scheme", Network: Computation in Neural Systems, 30(1-4), pp.125~147 (2019)
- S. Zhang, "Incipient fault detection for multiphase batch processes with limited batches", IEEE Transactions on Control Systems Technology, 27(1), pp.103~117 (2017)