多维应用特征融合的用户偏好预测.pdfVIP

*The High-Tech Research and Development Program of China under Grant No.2015AA01A202(国家高技术研究发展计划(863 计 划)); the Natural Science Foundation of China under Grant No.国家自然科学基金青年-面上连续资助项目); the Nat- ural Science Foundation of China under Grant No.国家自然科学基金创新研究群体项目). ISSN 1673-9418 CODEN JKYTA8 E-mail: fcst@ Journal of Frontiers of Computer Science and Technology 1673-9418/2000/00(00)-0000-00 Tel: +86-10 doi: 10.3778/j.issn.1673-9418.1609029 多维应用特征融合的用户偏好预测* 陈震鹏 1,2,陆璇 1,2, 李豁然 1,2,刘譞哲 1,2+ 1. 北京大学高可信软件技术教育部重点实验室, 北京 100871 2. 北京大学(天津滨海)新一代信息技术研究院, 天津 300450 Predicting User Preferences Based on Features of Android Apps * CHEN Zhenpeng 1,2 , LU Xuan 1,2 , LI Huoran 1,2 , LIU Xuanzhe 1,2+ 1. Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871, China 2. Beida (Binhai) Information Research, Tianjin 300450, China + Corresponding author: E-mail: liuxuanzhe@ CHEN Zhenpeng, LU Xuan, LI Huoran, LIU Xuanzhe. Predicting user preferences based on features of An- droid apps. Journal of Frontiers of Computer Science and Technology, 2000, 0(0): 1-000. Abstract: The rapid development of smartphones has brought an explosion of mobile applications (a.k.a. apps). Thus, it would be of app developers’ interest to predict user preferences of their apps in advance. This paper leve- rages the uninstallation/installation ratio as an implicit indicator and favorable rating as an explicit one of user pre- ferences. User-activity data involved in this study was collected froma popular app store in China, spanning five months from May to September, 2014. 9795 apps were selected, each covering no less than 50 active users. This paper employs30 features from 7 dimensions that might be correlated with user preferences, and extracts these fea- tures from the 9795 apps. Then, this paper builds Random-Forest classifiers to distinguish apps between high and low uninstallation/installation ratio