Wide & Deep Learning in Job Recommendation: An Empirical Study

• Published in: Information Retrieval Technology Vol. 10648; pp. 112 - 124
• Main Authors: Shi, Shaoyun, Zhang, Min, Lu, Hongyu, Liu, Yiqun, Ma, Shaopin
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Job recommendation; Recommender system; Wide & Deep Learning
• ISBN: 3319701444; 9783319701448
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-70145-5_9

Recommender systems have become more and more popular in recent years. Collaborative Filtering and Content-Based methods are widely used for a long time. Recently, some researchers introduced deep learning algorithms into recommender system. In this paper, we try to answer some questions about a novel recommender model, Wide & Deep Learning. Firstly, how should we select and feed in features? Secondly, how does Wide & Deep Learning work? Thirdly, how to joint-train the two parts of the network? Finally, how to conduct online training with new data? For all of these, we focus on the job recommendation task, which often suffers from the cold-start problem. The experiments give us the answers of these questions.