TY - JOUR
T1 - Version-sensitive mobile App recommendation
AU - Cao, Da
AU - Nie, Liqiang
AU - He, Xiangnan
AU - Wei, Xiaochi
AU - Shen, Jialie
AU - Wu, Shunxiang
AU - Chua, Tat Seng
PY - 2017/3
Y1 - 2017/3
N2 - Being part and parcel of the daily life for billions of people all over the globe, the domain of mobile Applications (Apps) is the fastest growing sector of mobile market today. Users, however, are frequently overwhelmed by the vast number of released Apps and frequently updated versions. Towards this end, we propose a novel version-sensitive mobile App recommendation framework. It is able to recommend appropriate Apps to right users by jointly exploring the version progression and dual-heterogeneous data. It is helpful for alleviating the data sparsity problem caused by version division. As a byproduct, it can be utilized to solve the in-matrix and out-of-matrix cold-start problems. Considering the progression of versions within the same categories, the performance of our proposed framework can be further improved. It is worth emphasizing that our proposed version progression modeling can work as a plug-in component to be embedded into most of the existing latent factor-based algorithms. To support the online learning, we design an incremental update strategy for the framework to adapt the dynamic data in real-time. Extensive experiments on a real-world dataset have demonstrated the promising performance of our proposed approach with both offline and online protocols. Relevant data, code, and parameter settings are available at http://apprec.wixsite.com/version.
AB - Being part and parcel of the daily life for billions of people all over the globe, the domain of mobile Applications (Apps) is the fastest growing sector of mobile market today. Users, however, are frequently overwhelmed by the vast number of released Apps and frequently updated versions. Towards this end, we propose a novel version-sensitive mobile App recommendation framework. It is able to recommend appropriate Apps to right users by jointly exploring the version progression and dual-heterogeneous data. It is helpful for alleviating the data sparsity problem caused by version division. As a byproduct, it can be utilized to solve the in-matrix and out-of-matrix cold-start problems. Considering the progression of versions within the same categories, the performance of our proposed framework can be further improved. It is worth emphasizing that our proposed version progression modeling can work as a plug-in component to be embedded into most of the existing latent factor-based algorithms. To support the online learning, we design an incremental update strategy for the framework to adapt the dynamic data in real-time. Extensive experiments on a real-world dataset have demonstrated the promising performance of our proposed approach with both offline and online protocols. Relevant data, code, and parameter settings are available at http://apprec.wixsite.com/version.
KW - Cold-start problem
KW - Data sparsity problem
KW - Mobile App recommendation
KW - Online environment
KW - Plug-in component
KW - Version progression
UR - http://www.scopus.com/inward/record.url?scp=84999738074&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2016.11.025
DO - 10.1016/j.ins.2016.11.025
M3 - Article
AN - SCOPUS:84999738074
VL - 381
SP - 161
EP - 175
JO - Information Sciences
JF - Information Sciences
SN - 0020-0255
ER -