News Recommendation Based on Click-Through Rate Prediction Model

Guiying Wei (), Yimeng Wei () and Jincheng Lei ()
Additional contact information
Guiying Wei: University of Science and Technology Beijing
Yimeng Wei: University of Science and Technology Beijing
Jincheng Lei: University of Science and Technology Beijing

A chapter in LISS 2020, 2021, pp 373-387 from Springer

Abstract: Abstract News recommendation is one of the most popular applications in recommendation system, but the traditional recommendation algorithms are challenged by news features such as high update frequency, time-sensitive, high proportion of inactive users, large scale of news data, etc. In this paper we propose a news recommendation system based on click-through rate prediction model which has been used in online advertising, and data features are processed by one-hot encoding and gradient boosting decision tree. Comparative experiments proved its effectiveness and superiority in news recommendation.

Keywords: News recommendation; Click-through rate prediction; Recommendation system; Gradient boosting decision tree; One-hot encoding (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-33-4359-7_27

Ordering information: This item can be ordered from
http://www.springer.com/9789813343597

DOI: 10.1007/978-981-33-4359-7_27

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().