Special Issue Published in International Journal of Trend in Research and Development (IJTRD), ISSN: 2394-9333, www.ijtrd.com National Conference on Emerging Trends in Computing (NCETC-2K17) organized by Department of Computer Applications, Godavari Institute of Engineering and Technology, Rajahmundry, A.P 7 th & 8 th April 2017 19 | Page Discovery of Ranking Fraud for Mobile Applications 1 G Siva Manikanta, 2 Mrs. Shrija Madhu 1 PG Student, 2 Associate Professor 1,2 Department of Computer Applications, Godavari Institute of Engineering and Technology, Rajahmundry, India Abstract— Ranking fraud in the mobile App market refers to fraudulent or misleading tricks which have a purpose of bumping up the Apps in the status list. Indeed, it becomes more and more frequent for App developers to use shady means, such as inflating their Apps‟ sales or posting phony App ratings, to commit ranking fraud. While the importance of preventing ranking fraud has been widely recognized, there is limited understanding and research in this area. To this end, in this paper, this provides a holistic view of ranking fraud and proposes a ranking fraud detection system for mobile Apps. Expressly, we first propose to accurately locate the ranking fraud by mining the 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, this 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, In this propose an optimization based aggregation method to integrate all the evidences for fraud detection. Finally, we evaluate the proposed system with real-world App data collected from the IOS App Store for a long time period. In the experiments, can validate the success of the planned system, and show the scalability of the detection algorithm as well as some regularity of ranking fraud activities. Keywords— Mobile Apps, ranking fraud detection, evidence aggregation, historical ranking records, rating and review. I. INTRODUCTION The number of mobile Apps has grown at a wonderful rate over the past few years. For example, as of the end of April 2013, there are more than 1.6 million Apps at Apple‟s App store and Google Play. To stimulate the development of mobile Apps, many App stores launched daily App leader boards, which display the chart rankings of most popular Apps. Indeed, the App leader board is one of the most important ways for promoting mobile Apps. A higher rank on the leader board usually leads to a huge number of downloads and million dollars in revenue. Therefore, App developers tend to explore various ways such as publicity campaigns to promote their Apps in order to have their Apps ranked as high as possible in such App leader boards. However, as a recent trend, instead of relying on traditional marketing solutions, under the trees App developer‟s alternative to some fraudulent means to purposely boost their Apps and eventually manipulate the chart rankings on an App store. This is usually implemented by using so called “bot farms” or “human water armies” to increase the App downloads ratings and reviews in a very short time. For example, an article from Venture Beat [1] reported that, when an App was promoted with the help of ranking manipulation, it could be propelled from number 1,800 to the top 25 in Apple‟s top free leader board and more than 50,000100,000 new users could be acquired within a couple of days. In fact, such ranking fraud raises great concerns to the mobile App business. For example, Apple has warned of fast down on App developers who commit ranking fraud [2] in the Apple‟s App store. In the literature, while there are some related work, such as web ranking spam detection [3], [4], online review spam detection , and mobile App recommendation the problem of detecting ranking fraud for mobile Apps is still under-explored. To fill this critical void, in this paper, propose to develop a ranking fraud detection system for mobile Apps. Along this line, purpose of identify several important challenges. First, ranking fraud does not always happen in the whole life cycle of an App, so In this need to detect the time when fraud happens. Such challenge can be regarded as detecting the local anomaly instead of global anomaly of mobile Apps. Second, due to the huge number of mobile Apps, it is hard to manually label ranking fraud for each App, so it is important to have a scalable way to automatically detect ranking fraud without using any standard information. Finally, due to the dynamic nature of chart rankings, it is not easy to identify and confirm the evidences linked to ranking fraud, which motivates us to discover some understood fraud pattern of mobile Apps as evidences. Indeed, our careful observation reveals that mobile Apps are not always ranked high in the leaderboard, but only in some leading events, which form different leading sessions. Note that can will introduce both leading events and leading sessions in detail later. In other words, ranking fraud usually happens in these leading sessions. Therefore, detecting ranking fraud of mobile Apps is actually to detect ranking fraud within leading sessions of mobile Apps. Specifically, In this first propose a simple yet successful algorithm to identify the leading sessions of each App based on its historical ranking records. Then, with the study of Apps‟ ranking behaviors, this find that the fraudulent Apps often have different ranking patterns in each leading session compared with normal Apps. Thus, the purpose of characterize some fraud evidences from Apps‟ historical ranking records, and develop three functions to extract such ranking based fraud evidences. Nonetheless, the ranking based evidences can be affected by App developers‟ status and some legitimate marketing campaigns, such as “limited-time discount”. As a result, it is not sufficient to only use ranking based evidences. Therefore, in this further propose two types of fraud evidences based on Apps‟ rating and review history, which reflect some difference patterns from Apps‟ historical rating and review records. In addition, this develops an invalid evidence-aggregation method to integrate these three types of evidences for evaluating the standing of leading sessions from mobile Apps. Fig. 1 shows the framework of our ranking fraud detection system for mobile Apps. It is importance noting that all the evidences are extracted by modeling Apps‟ ranking, rating and review behaviors through statistical hypotheses tests. The proposed framework is scalable and can be extended with other domain generated evidences for ranking fraud finding. Finally, In this evaluate the proposed system with real world App data collected from the Apple‟s App store for a long time period, i.e., more than two years. Experimental results show the effectiveness of the proposed system, the scalability of the detection algorithm as well as some regularity of ranking fraud activities. Overview: The rest of this paper is organized as follows. In Section 2, this introduces some preliminaries and how to mine leading sessions for mobile Apps. Section 3 presents how to