Discovery of Ranking Fraud for Mobile Apps




Abstract:
Ranking fraud in the mobile App market refers to fraudulent or deceptive activities which have a purpose of bumping up the Apps in the popularity 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, we provide a holistic view of ranking fraud and propose a ranking fraud detection system for mobile Apps. Specifically, 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, 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.










Introduction:
In a recent trend, instead of relying on traditional marketing solutions, shady App developers resort to some fraudulent means to deliberately 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 inflate the App downloads, ratings and reviews in a very short time. Indeed, our careful observation reveals that mobile Apps are not always ranked high in the leader board, but only in some leading events, which form different leading sessions. Note that we 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.















Existing System:
The analysis of Apps’ ranking behaviors, we find that the fraudulent Apps often have different ranking patterns in each leading session compared with normal Apps. Thus, we 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’ reputation and some legitimate marketing campaigns, such as “limited-time discount”. As a result, it is not sufficient to only use ranking based evidences.


Disadvantages:
·        In existing framework the leading session evidences are collude with duplicate evidences.
·        To extract the rating solution consumes lot of time as collection of leading session data.















Proposed System:
To extract and combine fraud evidences for ranking fraud detection by ranking based evidences, rating based evidences and review based evidences. To study the performance of ranking fraud detection by each approach, we set up the evaluation as follows. First, for each approach, we selected 50 top ranked leading sessions (i.e., most suspicious sessions), 50 middle ranked leading sessions (i.e., most uncertain sessions), and 50 bottom ranked leading sessions (i.e., most normal sessions) from each data set. Then, we merged all the selected sessions into a pool which consists 587 unique sessions from 281 unique Apps in “Top Free 300” data set, and 541 unique sessions from 213 unique Apps in “Top Paid 300” data set. Second, we invited five human evaluators who are familiar  with Apple’s App store and mobile Apps to manually label the selected leading sessions with score 2 (i.e., Fraud), 1 (i.e., Not Sure) and 0 (i.e., Non-fraud). Specifically, for each selected leading session, each evaluator gave a proper score by comprehensively considering the profile information of the App (e.g., descriptions, screenshots), the trend of rankings during this session, the App leader board information during this session, the trend of ratings during this session, and the reviews during this session.
Advantages:
ü Data redundancy is removed at each session of proposed framework session.
ü Observation results are stored securely.

Software Requriments
Front End: HTML5, CSS3, Bootstrap
Back End: PHP, MYSQL
Control End: Angular Java Script
Tool: Android SDK, Xampp, Eclipse




codeshoppy.com
http://codeshoppy.com/android-ieee-projects-titles-2017-2018.html
Android Youtube Channel
arudhrainnovations.com

contact@codeshoppy.com
9790675343



Comments

Post a Comment

Popular posts from this blog

ecriminal Identification Using Face Recognition Based Mobile App

Abstract Criminals identification using face recognition based mobile app to search and identify criminal details. In the existing system finding the criminal and identify the background data is diffcuilt, which leads to time taking process and lack of accurcy. The proposed mobile applications contains criminal details such as name, case no, photo and etc. Police shall search using face recognition and other details easily through mobile. This research proposes an unobtrusive means of acquiring and recording shoeprints of anyone who enters the safe room. Existing System ·          It need employment as the human efforts. ·          In existing system works on manual process which is a time taking process and data organizing is not efficient.  Proposed System ·          The system allows automate management system. ·     ...
Read more

Bridge between Investor and Business people

Investment in India is a concept based on business purpose. In my project I will be providing     platform to the investors and also connecting the people with good business concepts. This in turn will evolve how much to invest and where to invest the money with good returns on investment. Here providing two forms - one for investors and another one for business people with contact details. There are situation when the people have excess funds they will try to park this amount in Banks or Gold.   Here, I am exploring the possibility of investing these excess funds directly to the business connecting the investor and the business persons.   I am developing the application which will connect the investor and the business people and vice-versa.   I will be charging for usage of my application from both the ends. The need for developing this project was to bridge the huge communicational gap between the business people and investors and also with no time...
Read more

Mobile App for Soil with suitable farming agent and distributor location

ABSTRACT The Soil Screening Guidance incorporates readily obtainable site data into simple, standardized equations to derive site-specific screening levels for selected contaminants and exposure pathways. Admin enter the soil detail and distributor details. User can view those soil details and distributor details. Admin collect all information about soil and distributor location also. 1.1   Objectives The objective of this project is user friendly app for people. Here attach all details about soil and distributor places. 1.2   System Specifications Hardware Requirements:- Ø Android OS Software Requirements: - Operating System :    Android OS Front-End             :     HTML, CSS, and JS Back-End              :     Angular JS, PHP, MYSQL Tool         ...
Read more