Search

To boost the popularity of Apps, dishonest or fraudulent behaviors characterize ranking fraud in the mobile Application industry. To conduct ranking fraud, which is becoming more common place so that Application producers are increasingly using dubious methods, ' revenues or publishing bogus App evaluations, though ranking fraud is generally acknowledged, there is a lack of knowledge and study in this field. We utilized the Rank Aggregation Algorithm to further evaluate the ranking system for this purpose in this study. For starters, we recommend that mobile App active times, i.e. leading sessions, be used to precisely discover ranking fraud in search results The local abnormality of App ranking scan be detected using such coaching sessions instead of the global anomaly. By simulating Apps' rating and review behaviors using statistical hypothesis testing, we study three sorts of data: a ranking-based dataset, a rating-based dataset, and are view-based data set. In addition, we present an optimization-based aggregation technique for detecting fraud. [ABSTRACT FROM AUTHOR]