Абстрактный

Ranking Fraud Detection for Mobile Apps using Evidence Aggregation and Humming Bird algorithm

S.Kalaiarasi, Swetha Ganesh, Praveena.C.H, Vaishali.T

There are a lot a number of apps that are increasing every day over the past few years. The owners also resort to shady and fraudulent activities to increase the ranking of the apps in the popularity list. There is limited understanding in this area though the prevention of fraud has been widely is recognized. In Proposed we are predicting how many users using the particular apps based on their downloading the limitation then we are providing all kind of supportable apps like Android, Windows, IOS, and Symbian. In this paper, we provide a view of ranking fraud for mobile Apps. The users are provided a limitation of using the apps. The user can download the apps by providing the secret key which is provided by the admin. And when the users are trying to misuse the apps by downloading it a number of times, the user information is send to the Admin. We are also predicting how many users are using the particular App. Also, in the existing system even if the user views the app details, the app ranking is being increased. But in this system, only if the user downloading the App will increase the ranking of the particular app. The usage of apps can also be tracked using the leading apps and the graph of the particular app can also be tracked.