Algorithms and System Architecture for Immediate Personalized News Recommendations release_qnhbxxabrzd3ne4v4wrx7ujpku

by Takeshi Yoneda, Shunsuke Kozawa, Keisuke Osone, Yukinori Koide, Yosuke Abe, Yoshifumi Seki

Released as a article .

2019  

Abstract

Personalization plays an important role in many services, just as news does. Many studies have examined news personalization algorithms, but few have considered practical environments. This paper provides algorithms and system architecture for generating immediate personalized news in a practical environment. Immediacy means changes in news trends and user interests are reflected in recommended news lists quickly. Since news trends and user interests rapidly change, immediacy is critical in news personalization applications. We develop algorithms and system architecture to realize immediacy. Our algorithms are based on collaborative filtering of user clusters and evaluate news articles using click-through rate and decay scores based on the time elapsed since the user's last access. Existing studies have not fully discussed system architecture, so a major contribution of this paper is that we demonstrate a system architecture and realize our algorithms and a configuration example implemented on top of Amazon Web Services. We evaluate the proposed method both offline and online. The offline experiments are conducted through a real-world dataset from a commercial news delivery service, and online experiments are conducted via A/B testing on production environments. We confirm the effectiveness of our proposed method and also that our system architecture can operate in large-scale production environments.
In text/plain format

Archived Files and Locations

application/pdf  756.0 kB
file_mgtydd3jpvhgrcino2zbsiloii
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-09-03
Version   v1
Language   en ?
arXiv  1909.01005v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5a766812-bb63-4e18-8e26-77bfc587671a
API URL: JSON