Abstract
Ranking fraud in the mobile App market refers to fraudulent activities which have a purpose of raise the apps in the popularity list. In fact, it is easy for App developers to boost their Apps sales or posting forged App ratings, to commit ranking fraud. To prevent this ranking fraud we provide a holistic view of ranking fraud detection system for mobile Apps. Specifically, we first propose to locate the ranking fraud by mining the leading sessions, of mobile Apps. Such leading sessions can be leveraged for detecting the abnormality or irregularity 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 addition, we propose an optimization based aggregation method to integrate all the evidences for fraud detection.
Keywords
Mobile Apps
ranking fraud detection
evidence aggregation
rating and review.
Authors
How to Cite this Article
N.Bhavani, A.Gayathri, T.Eswari, K.Kalaivani, K.Kalaivani (2016).
"A HOLISTIC VIEW OF RANKING FRAUD DETECTION SYSTEM FOR MOBILE APPS".
International Journal of Contemporary Research in Computer Science and Technology,
2(3), pp. 605-608.
