Hybrid employment recommendation algorithm based on Spark

2nd Annual International Conference on Information System and Artificial Intelligence

物理学;计算机科学

Li, Zuoquan^1 ; Lin, Yubei^2 ; Zhang, Xingming^1

School of Computer Science and Engineering, South China University of Technology, Higher Education Mega Centre, Panyu District Guangzhou, China^1

School of Software Engineering, South China University of Technology, Higher Education Mega Centre, Panyu District Guangzhou, China^2

关键词: Collaborative filtering recommendations;    Content-based algorithm;    Content-based recommendation;    Employment recommendations;    Hier-archical clustering;    Hybrid recommendation;    Real-time application;    Recommendation accuracy;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/887/1/012045/pdf
DOI  :  10.1088/1742-6596/887/1/012045

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Aiming at the real-time application of collaborative filtering employment recommendation algorithm (CF), a clustering collaborative filtering recommendation algorithm (CCF) is developed, which applies hierarchical clustering to CF and narrows the query range of neighbour items. In addition, to solve the cold-start problem of content-based recommendation algorithm (CB), a content-based algorithm with users' information (CBUI) is introduced for job recommendation. Furthermore, a hybrid recommendation algorithm (HRA) which combines CCF and CBUI algorithms is proposed, and implemented on Spark platform. The experimental results show that HRA can overcome the problems of cold start and data sparsity, and achieve good recommendation accuracy and scalability for employment recommendation.