ABSTRACT
At present, the recommendation algorithm of power integration mall is often limited to users' personal preferences and historical choices, and it is difficult to capture the change information of users' behavior exchange trend, so it is easy to lead the recommendation model into local optimum. In order to solve the above problems, a method of power integral merchandise recommendation based on inverse reward learning optimization is proposed. The algorithm constructs a latent customer mining model to cluster users in multi-dimension, extracts the relevant feature information of different user groups, and implements the convertible merchandise recommendation for different user groups with three-dimensional rating recommendation algorithm. Subsequently, an optimal recommendation model based on inverse reward feedback learning is adopted to guide the next recommendation behavior according to the reward plastic function formed by historical exchange records. On the premise of satisfying users' individual exchange preferences, on the one hand, it avoids the limitation of the traditional recommendation algorithm which leads to the recommendation of goods, on the other hand, it enlarges the range of users' choice of exchange by the direction of recommendation formed by the overall users' exchange preferences. The experimental results show that the model can improve the success rate of customer converting commodities, and illustrate its feasibility and effectiveness.
- Zhai H T and Wang X M. 2019. Research on collaborative recommendation algorithm based on implicit feedback LDA model. Computer Technology and Development. 29, 6 (Jun. 2019), 1--6.Google Scholar
- Wang R, Cheng H K and Jiang Y, et al. 2019. A novel matrix factorization model for recommendation with LOD-based semantic similarity measure. Expert Systems With Applications, 123 (Jun. 2019), 70--81.Google Scholar
- Liu F Y, Gao X Q and Zhang Z. 2017. Improved bayesian probabilistic model based recommender system. Computer Science. 44, 5 (May. 2017), 285--289.Google Scholar
- Zhang P F, Zhang Z J and Tian T, et al. 2019. Collaborative filtering recommendation algorithm integrating time windows and rating predictions. Applied Intelligence, 48, 8 (Jul. 2019), 3146--3157.Google Scholar
- Zhao Q Q, Lu K and Wang B. 2013. A memory based collaborative filtering algorithm via propagation. Chinese Journal of Computers. 36,3 (Mar. 2013), 671--676.Google Scholar
- Wang R Q, Pan J and Feng J J.2018. Recommendation algorithm based on trust computation and matrix factorization. Pattern Recognition and Artificial Intelligence. 31, 9 (Sep. 2018), 786--796.Google Scholar
- Hao Y X and Sun Y R. 2018. K-nearest neighbor matrix factorization for recommender systems. Journal of Chinese Mini-Micro Computer Systems. 39, 4 (Apr. 2018), 755--758.Google Scholar
- Zhang S L. 2017. Survey of intelligent recommendation algorithms. Journal of Changchun Normal University. 36, 6 (Jun. 2017), 51--54.Google Scholar
- Huang L W, Jiang B T and Lv S Y, et al. 2018. Survey on deep learning based recommender systems. Chinese Journal of Computers. 427, 7 (Mar. 2018), 191--219.Google Scholar
- Hong Y and Li Z Y.2010. A collaborative filtering recommendation algorithm based on forgetting curve. Journal of Nanjing University. 46, 5 (Sep. 2010), 520--527.Google Scholar
- Jiao H M, Chen X F and Chen X, et al.2017. Collaborative filtering based on bayesian network and cognitive feedback. Control Engineerin of China. 24, 7 (Jul. 2017), 1310--1317.Google Scholar
- Zhang P F, Wang Y G and Zhang Z J.2019. Research on personalized recommendation algorithm based on label and multi-information. Computer Engineering and Applications. 55, 5 (May. 2019), 159--165.Google Scholar
Index Terms
- Power Integration Mall Recommendation Model Based on Reverse Reward Feedback Learning Optimization
Recommendations
Using Multidimensional Clustering Based Collaborative Filtering Approach Improving Recommendation Diversity
WI-IAT '12: Proceedings of the The 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology - Volume 03In this paper, we present a hybrid recommendation approach for discovering potential preferences of individual users. The proposed approach provides a flexible solution that incorporates multidimensional clustering into a collaborative filtering ...
A High Efficient Recommendation Algorithm Based on LDA
HCC 2016: Revised Selected Papers of the Second International Conference on Human Centered Computing - Volume 9567As for the low recommendation degree of the traditional collaborative filtering recommendation algorithm, a high efficient recommendation algorithm was put forward based on LDA. A new interest layer is added between the user layer and the project layer ...
A Cold-Start Recommendation Algorithm Based on New User's Implicit Information and Multi-attribute Rating Matrix
HIS '09: Proceedings of the 2009 Ninth International Conference on Hybrid Intelligent Systems - Volume 02Traditional collaborative filtering recommendation algorithms face the cold-start problem. A collaborative filtering recommendation algorithm based on the implicit information of the new users and multi-attribute rating matrix is proposed to solve the ...
Comments