论文信息 - LBS and Multidimensional Scoring Based Recommendation Algorithm

LBS and Multidimensional Scoring Based Recommendation Algorithm

With the rapid development of the national economy, China's car ownership is increasing, so the demand and value of the automobile after-service market are constantly rising. How to integrate the existing automobile maintenance and repair services to provide fast and convenient environment for car owners has become a difficult problem. Firstly, in view of the sparsity of user-store scoring matrix, this paper proposes geolocation-based matrix partition to reduce the running time. Then demographic-based recommendation algorithm is employed to solve the 'cold start' problem existed in user-based collaborative filtering recommendation algorithm. Finally, in terms of different users' concerns, a dynamic multidimensional scoring model is proposed. The experiment is conducted on the Meituan data, and the results show that the proposed method achieves good performance in recommendation efficiency, precision and recall. Meanwhile, this method also brings light to the future automobile after-service market.

Dongqi Wang | Dongming Chen | Xinyu Huang | Qinghua Meng | Xiaoguang Wu

[1] Seung-won Hwang,et al. Cold-Start Aware User and Product Attention for Sentiment Classification , 2018, ACL.

[2] Mao Ye,et al. Exploiting geographical influence for collaborative point-of-interest recommendation , 2011, SIGIR.

[3] T. Adilakshmi,et al. Music Recommendation System with User-based and Item-based Collaborative Filtering Technique , 2017, Indonesian Journal of Electrical Engineering and Informatics (IJEEI).

[4] Gediminas Adomavicius,et al. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[5] Douglas B. Terry,et al. Using collaborative filtering to weave an information tapestry , 1992, CACM.

[6] Li Peng. Survey of Collaborative Filtering Algorithms , 2009 .

[7] Du Xiaoyong,et al. Recommendation algorithm combining the user-based classified regression and the item-based filtering , 2006 .

[8] Hemant Jain,et al. Integrating geographical and temporal influences into location recommendation: a method based on check-ins , 2019, Inf. Technol. Manag..