TY - JOUR
T1 - A user similarity-based Top-N recommendation approach for mobile in-application advertising
AU - Hu, Jinlong
AU - Liang, Junjie
AU - Kuang, Yuezhen
AU - Honavar, Vasant
N1 - Funding Information:
This work is supported in part by the Science and Technology Planning Project of Guangdong Province , China [No. 2013B090500087 , No. 2014B010112006 ], the Scientific Research Joint Funds of Ministry of Education of China and China Mobile [No. MCM20150512 ], and the State Scholarship Fund of China Scholarship Council [No. 201606155088 ] and the Edward Frymoyer Endowed Chair in Information Sciences and Technology at Pennsylvania State University [held by Professor Honavar].
Publisher Copyright:
© 2018
PY - 2018/11/30
Y1 - 2018/11/30
N2 - Ensuring scalability of recommender systems without sacrificing the quality of the recommendations produced, presents significant challenges, especially in the large-scale, real-world setting of mobile ad targeting. In this paper, we propose MobRec, a novel two-stage user similarity based approach to recommendation which combines information provided by slowly-changing features of the mobile context and implicit user feedback indicative of user preferences. MobRec uses the contextual features to cluster, during an off-line stage, users that share similar patterns of mobile behavior. In the online stage, MobRec focuses on the cluster consisting of users that are most similar to the target user in terms of their contextual features as well as implicit feedback. MobRec also employs a novel strategy for robust estimation of user preferences from noisy clicks. Results of experiments using a large-scale real-world mobile advertising dataset demonstrate that MobRec outperforms the state-of-the-art neighborhood-based as well as latent factor-based recommender systems, in terms of both scalability and the quality of the recommendations.
AB - Ensuring scalability of recommender systems without sacrificing the quality of the recommendations produced, presents significant challenges, especially in the large-scale, real-world setting of mobile ad targeting. In this paper, we propose MobRec, a novel two-stage user similarity based approach to recommendation which combines information provided by slowly-changing features of the mobile context and implicit user feedback indicative of user preferences. MobRec uses the contextual features to cluster, during an off-line stage, users that share similar patterns of mobile behavior. In the online stage, MobRec focuses on the cluster consisting of users that are most similar to the target user in terms of their contextual features as well as implicit feedback. MobRec also employs a novel strategy for robust estimation of user preferences from noisy clicks. Results of experiments using a large-scale real-world mobile advertising dataset demonstrate that MobRec outperforms the state-of-the-art neighborhood-based as well as latent factor-based recommender systems, in terms of both scalability and the quality of the recommendations.
UR - http://www.scopus.com/inward/record.url?scp=85044723859&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044723859&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2018.02.012
DO - 10.1016/j.eswa.2018.02.012
M3 - Article
AN - SCOPUS:85044723859
SN - 0957-4174
VL - 111
SP - 51
EP - 60
JO - Expert Systems With Applications
JF - Expert Systems With Applications
ER -