Time-Weighted Collaborative Filtering Algorithm Based on Improved Mini Batch K-Means Clustering

Abstract:

The traditional collaborative filtering recommendation algorithm has the defects of sparse score matrix, weak scalability and user interest deviation, which lead to the low efficiency of algorithm and low accuracy of score prediction. Aiming at the above problems, this paper proposed a time-weighted collaborative filtering algorithm based on improved Mini Batch K-Means clustering. Firstly, the algorithm selected the Pearson correlation coefficient to improve the Mini Batch K-Means clustering, and used the improved Mini Batch K-Means algorithm to cluster the sparse scoring matrix, calculated the user interest score to complete the filling of the sparse matrix. Then, considering the influence of user interest drift with time, the algorithm introduced the Newton cooling time-weighted to improve user similarity. And then calculated user similarity based on the filled score matrix, which helped to get the last predicted score of unrated items The experimental results show that, compared with the traditional collaborative filtering algorithms, the mean absolute error of Proposed improved algorithm is d, and the Precision, Recall and F1 value of MBKT-CF also get a large improvement, which has a higher rating prediction accuracy.

• Periodical: Advances in Science and Technology (Volume 105)
• Pages: 309-317
• DOI: https://doi.org/10.4028/www.scientific.net/AST.105.309
• Online since: April 2021
• Authors: Xue Han*, Zhong Wang, Hui Jun Xu
• Keywords: Collaborative Filtering, Mini Batch K-Means Clustering, Newton's Law of Cooling, Pearson Correlation Coefficient, Predictive Padding

References

[1] Wang Daoping, Jiang Zhongyang and Zhang Boqing. Collaborative filtering algorithm based on gray correlation analysis and time factor[J]. Data Analysis and Knowledge Discovery, 2018, 2(6):102-9.

[2] Xiao Wenqiang, Yao Shijun and Wu Shangming. Improved top-N collaborative filtering recommendation algorithm[J]. Application Research of Computers, 2018, 35(1):105-8,112.

[3] Yang Xingyu, Li Huaping and Zhang Yubo.Collaborative filtering algorithm based on clustering and random forests[J]. Computer Engineering and Applications, 2018,54(16):152-7.

[4] Luo Xin, Zhou Mengchu, Xia Yunni, et al. An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems[J]. IEEE Trans on Industrial Informatics,2014,10(2):1273-84.

DOI: 10.1109/tii.2014.2308433

[5] Pan Taotao, Weng Feng and Liu Qinrang. Collaborative filtering recommendation algorithm based on rating matrix filling and item predictability[J]. Acta Automatica Sinica, 2017,43(9):1597-606.

[6] Berkani L. Social-Based collaborative recommendation: bees swarm optimization based clustering approach [C]// International Conference on Model and Data Engineering. Springer, Cham, 2019,156-171.

DOI: 10.1007/978-3-030-32065-2_11

[7] Zhang Yanmei, Wang Lu. Research on social tagging recommendation algorithm incorporated with user interest change[J]. Computer Engineering,2014,40(11):318-21.

[8] Zeng An, Gao Chengsi and Xu Xiaoqiang. Collaborative filtering algorithm incorporating time factor and user preference properties[J]. Computer Science,2017,44(9):243-9.

[9] Yuan Hanning, Zhou Tong, Han Yanni, et al. Collaborative recommendation algorithm based on MI clustering[J]. Geomatics and Information Science of Wuhan University, 2015, 40(2): 253-7.

[10] Kant S, Mahara T, Jain V K, et al. Fuzzy logic based similarity measure for multimedia contents recommendation [J]. Multimedia Tools and Applications, 2019, 78 (4): 4107-4130.

DOI: 10.1007/s11042-017-5260-2

[11] Sakib N, Ahmad R B, Haruna K. A Collaborative Approach Toward Scientific Paper Recommendation Using Citation Context[J]. IEEE Access, 2020, 8: 51246-51255.

DOI: 10.1109/access.2020.2980589