Tao Zeng
ABSTRACT
Existing recommendation systems mainly focus on the improvement of accuracy but neglect to involve non-popular items, which leads to the unfairness problem of recommendation results. More specifically, the low exposure rate of non-popular items impairs the diversity of recommendation results and thus weakens the customer experience for online e-commerce platforms. To address this problem, we propose a Fair Personalized Recommendation Algorithm(FPRA) combining improved Matrix Factorization and Back-Propagation Neural Network, which can simultaneously acquire both the accuracy and the fairness of recommendation results. In the FPRA, popular items and non-popular items are separated according to a pre-defined proportion. On the one hand, we consider that the influence of scenario factors (i.e., browsing location, clicking number, etc.) will generate users’ assessment bias for popular items, and we leverage BP Neural Networks to train the bias when recommending popular items. On the other hand, we design a new function, namely Fairness & Accuracy function, to achieve the goal that non-popular items will be presented to customers more frequently. Using this function, the goal can be achieved by searching for the optimal solution under the condition constraints. Experimental results show that the effectiveness of our proposed that FPRA greatly outperforms other baseline methods.
Supplemental Material
Available for Download
- [1] Bauer J, Biolo G, Cederholm T, et al. Evidence-based recommendations for optimal dietary protein intake in older people: a position paper from the PROT-AGE Study Group[J]. Journal of the american Medical Directors association, 2013, 14(8): 542-559.Google Scholar
- [2] S. B. Roy, S. Amer-Yahia, A. Chawla, G. Das, and C. Yu, “Space efficiency in group recommendation,” The VLDB Journal, vol. 19, no. 6, pp. 877–900, 2010.Google Scholar
- [3] S. Amer-Yahia, S. B. Roy, A. Chawlat, G. Das, and C. Yu, “Group recommendation: Semantics and efficiency,” Proceedings of the VLDB Endowment, vol. 2, no. 1, pp. 754–765, 2009.Google ScholarDigital Library
- [4] T. N. Nguyen and F. Ricci, “Situation-dependent combination of long-term and session-based preferences in group recommendations: an experimental analysis,” in Proceedings of the 33rd Annual ACM Symposium on Applied Computing, 2018, pp. 1366–1373.Google ScholarDigital Library
- [5] N. Capuano, F. Chiclana, E. Herrera-Viedma, H. Fujita, and V. Loia, “Fuzzy group decision making for influence-aware recommendations,” Computers in Human Behavior, vol. 101, pp. 371–379, 2019.Google ScholarCross Ref
- [6] J. Castro, J. Lu, G. Zhang, Y. Dong, and L. Martínez, “Opinion dynamics-based group recommender systems,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 48, no. 12, pp. 2394–2406, 2017.Google Scholar
- [7] Christensen I, Schiaffino S, Armentano M. Social group recommendation in the tourism domain[J]. Journal of Intelligent Information Systems, 2016, 47(2): 209-231.Google ScholarDigital Library
- [8] B.-H. Li, A.-M. Zhang, W. Zheng, S. Wan, X.-L. Qin, X. Li, and H.-L. Yin, “Grip: a group recommender based on interactive preference model,” Journal of Computer Science and Technology, vol. 33, no. 5, pp. 1039–1055, 2018.Google ScholarCross Ref
- [9] H. Xu, Y. Ding, J. Sun, K. Zhao, and Y. Chen, “Dynamic group recommendation based on the attention mechanism,” Future Internet, vol. 11, no. 9, p. 198, 2019.Google ScholarCross Ref
- [10] H. Steck, “Calibrated recommendations,” in Proceedings of the 12th ACM conference on recommender systems, 2018, pp. 154–162.Google ScholarDigital Library
- [11] M. Kaya and D. Bridge, “A comparison of calibrated and intent-aware recommendations,” in Proceedings of the 13th ACM Conference on Recommender Systems, 2019, pp. 151–159.Google ScholarDigital Library
- [12] R. Konishi, F. Nakamura, and Y. Kiyoki, “Calibrated web personalization with adaptive recurrent computing,” in 2020 IEEE 14th International Conference on Semantic Computing (ICSC). IEEE, 2020, pp. 9–16.Google ScholarCross Ref
- [13] I. Rabiu, N. Salim, A. Da’u, and A. Osman, “Recommender system based on temporal models: a systematic review,” Applied Sciences, vol. 10, no. 7, p. 2204, 2020.Google ScholarCross Ref
- [14] Z. Farahi, A. Moeini, and A. Kamandi, “Bloofi representation for item/user in recommender systems,” in 2019 5th International Conference on Web Research (ICWR). IEEE, 2019, pp. 67–73.Google ScholarCross Ref
- [15] K. Huang, Y. Liu, S. Nepal, Y. Fan, S. Chen, and W. Tan, “A novel equitable trustworthy mechanism for service recommendation in the evolving service ecosystem,” in International Conference on Service-Oriented Computing. Springer, 2014, pp. 510–517.Google ScholarDigital Library
- [16] Z. Jia, Y. Yang, W. Gao, and X. Chen, “User-based collaborative filtering for tourist attraction recommendations,” in 2015 IEEE International Conference on Computational Intelligence & Communication Technology. IEEE, 2015, pp. 22–25.Google ScholarCross Ref
- [17] Zhao, Zhi-Dan, and Ming-Sheng Shang. ”User-based collaborative-filtering recommendation algorithms on hadoop.” 2010 third international conference on knowledge discovery and data mining. IEEE, 2010.Google Scholar
- [18] H. Abdollahpouri and R. Burke, “Multi-stakeholder recommendation and its connection to multi-sided fairness,” arXiv preprint arXiv:1907.13158, 2019.Google Scholar
- [19] Burke R. Multisided fairness for recommendation[J]. arXiv preprint arXiv:1707.00093, 2017.Google Scholar
Recommendations
A time-sensitive personalized recommendation method based on probabilistic matrix factorization technique
Personalized recommender systems are the most effective way to solve the problem of information overload. The majority of traditional personalized recommender systems employ the collaborative filtering (CF) approach. CF leverages users' behaviors to ...
Attributes coupling based matrix factorization for item recommendation
Recommender systems have attracted lots of attention since they alleviate the information overload problem for users. Matrix factorization is one of the most widely employed collaborative filtering techniques in the research of recommender systems due ...
A preprocessing matrix factorization on collaborative filtering based library book recommendation system
DSIT '18: Proceedings of the 2018 International Conference on Data Science and Information TechnologyNowadays, recommendation systems are widely used to recommend items to the users that are specific to their individual preferences and most appropriate. For this reason, many academic libraries try to establish an effectiveness and efficiency book ...
Comments