Authors:- Yalavarthipati Shaik Reshma, B Lakshmikanth
Abstract:- The Mobile App is a very popular and well known concept due to the rapid advancement in the mobile technology. Due to the large number of mobile Apps, ranking fraud is the key challenge in front of the mobile App market. Ranking fraud refers to fraudulent or vulnerable activities which have a purpose of bumping up the Apps in the popularity list. While the importance and necessity of preventing ranking fraud has been widely recognized. In the existing system the leading event and leading session of an app is identified from the collected historical records. Then three different types of evidences are collected from the user feedbacks namely ranking based evidence, rating based evidence and review based evidence. These three evidences are aggregated by using evidence aggregation method. In the proposed system additionally, we are proposing two enhancements. Firstly, we are using Approval of scores by the admin to identify the exact reviews and rating scores. Secondly, the fake feedbacks by a same person for pushing up that app on the leader board are restricted. Two different constraints are considered for accepting the feedback given to an application. The first constraint is that an app can be rated only once from a user login and the second is implemented with the aid of IP address that limits the number of user login logged per day. Finally, the proposed system will be evaluated with real-world App data which is to be collected from the App Store for a long time period.
Active periods, namely leading sessions, of mobile Apps. Such leading sessions can be leveraged for detecting the local anomaly instead of global anomaly of app rankings. Furthermore, we investigate three types of evidences, i.e., ranking based evidences, rating based evidences and review based evidences, by modeling apps’ ranking, rating and review behaviors through statistical hypotheses tests.
In Rating Based Evidences, specifically, after an App has been published, it can be rated by any user who downloaded it. Indeed, user rating is one of the most important features of App advertisement. An App which has higher rating may attract more users to download and can also be ranked higher in the leader board. Thus, rating manipulation is also an important perspective of ranking fraud. In Review Based Evidences, besides ratings, most of the App stores also allow users to write some textual comments as App reviews. Especially, this paper proposes a simple and effective algorithm to recognize the leading sessions of each mobile App based on its historical ranking records. This is one of the fraud evidence. Also, rating and review history, which gives some anomaly patterns from apps historical rating and reviews records.
The rest of the paper is organized as follows: Section II, presents the literature survey over the related work. In section III, proposed system is presented in section IV, implementation for each modules. Finally, the section V concludes the review paper.