期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2016
卷号：5
期号：3
页码：0745-0748
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Ranking fraud in the mobile App business arcade refers to fraudulent or false activities which have a purpose of hitting up the Apps in the popularity list. Indeed, it becomes more and more frequent for App creators to use shady means, such as inflating their App's sales or deflating other apps through posting of phony ratings, to commit ranking fraud. While the significance of preventing fraud has been widely acknowledged there is limited recognition and research in this area.we first propose to accurately locate the ranking fraud by mining the lively periods, namely leading sessions, of mobile Apps. Such leading sessions can be leveraged for detecting the local irregularity instead of global irregularity of App rankings. Furthermore, we explore three types of facts, i.e., ranking, rating and review based facts by molding Apps' ranking, rating and review behaviors through numerical hypotheses tests. In addition, we propose an optimization based accumulation method to integrate all the facts for fraud detection. Finally, we evaluate the proposed system with real-world App data collected from the iOS App Store for a long time period. In the experiments, we validate the effectiveness of the proposed system, and show the scalability of the detection algorithm as well as some predictability of ranking fraud activities.
