Discovery of Ranking Fraud for Mobile Apps Evidence Aggregation Based Ranking Fraud Detection (EA-RFD)

Main Article Content

Patil Gokul A., Shewale Sandip K, Barhate Roshan D., Patil Tushar S., Prof. S.A.Handore


Ranking fraud within the mobile App market refers to dishonest or deceptive activities that have a purpose of bumping up the Apps within the quality list. Indeed, it becomes additional and additional frequent for App developers to use shady suggests that, like inflating their Apps? sales or posting phony App ratings, to commit ranking fraud. Whereas the importance of preventing ranking fraud has been well known, there's restricted understanding and analysis during this space. to the present finish, during this paper, we offer a holistic read of ranking fraud and propose a ranking fraud detection system for mobile Apps. Specifically, we tend to 1st propose to accurately find the ranking fraud by mining the active periods, specifically leading sessions, of mobile Apps. Such leading sessions will be leveraged for detective work the native anomaly rather than world anomaly of App rankings. Moreover, we tend to investigate 3 forms of evidences, i.e., ranking based mostly evidences, rating {based based mostly primarily based mostly} evidences and review based evidences, by modeling Apps? ranking, rating and review behaviors through applied mathematics hypotheses tests. Additionally, we tend to propose AN optimization based mostly aggregation methodology to integrate all the evidences for fraud detection. Finally, we tend to evaluate the projected system with real-world App knowledge collected from the iOS App Store for an extended fundamental measure. Within the experiments, we tend to validate the effectiveness of the projected system, and show the quantifiability of the detection algorithmic program furthermore as some regularity of ranking fraud activities.

Article Details

How to Cite
, P. G. A. S. S. K. B. R. D. P. T. S. P. S. “Discovery of Ranking Fraud for Mobile Apps Evidence Aggregation Based Ranking Fraud Detection (EA-RFD)”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 5, no. 3, Mar. 2017, pp. 440-4, doi:10.17762/ijritcc.v5i3.325.