Scribd
Upload
159 views10 pages

Discovery of Ranking Fraud For

This document proposes a system to detect ranking fraud for mobile apps. It begins with an introduction to the problem of ranking fraud and an abstract summarizing the goals. It then describes the limitations of existing systems, which focus on web or review spam but cannot detect ranking fraud patterns in apps over time. The proposed system aims to identify fraudulent periods ("leading sessions") in apps' histories and integrate multiple sources of evidence like rankings, ratings, and reviews using an optimization method. It is intended to be scalable and its effectiveness is evaluated using real app data. Hardware requirements include a Pentium PC and 80GB hard drive while the software uses Java/J2EE, Netbeans IDE, and MySQL database.

Uploaded by

Anubhav Goel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
159 views10 pages

Discovery of Ranking Fraud For

This document proposes a system to detect ranking fraud for mobile apps. It begins with an introduction to the problem of ranking fraud and an abstract summarizing the goals. It then describes the limitations of existing systems, which focus on web or review spam but cannot detect ranking fraud patterns in apps over time. The proposed system aims to identify fraudulent periods ("leading sessions") in apps' histories and integrate multiple sources of evidence like rankings, ratings, and reviews using an optimization method. It is intended to be scalable and its effectiveness is evaluated using real app data. Hardware requirements include a Pentium PC and 80GB hard drive while the software uses Java/J2EE, Netbeans IDE, and MySQL database.

Uploaded by

Anubhav Goel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Discovery of Ranking Fraud for

Mobile Apps
Presented By
Anubhav Goel
Aditi Oli
Archisha
Vishal Goel
TABLE OF CONTENTS
 Abstract
 Existing System
 Proposed System
 Hardware Requirements
 Software Requirements
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.
 A holistic view of ranking fraud and propose a ranking
fraud detection system for mobile Apps.
 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.
Existing System
 In Existing system, while there are some related
work, such as web ranking spam detection, online
review spam detection and mobile App
recommendation, the problem of detecting ranking
fraud for mobile Apps is still under-explored.
 This study can be grouped into three categories.
 first category :- web ranking spam detection.
 second category :-detecting online review spam.
 third category:-mobile App recommendation
Disadvantages
 Although some of the existing approaches can be
used for anomaly detection from historical rating and
review records, they are not able to extract fraud
evidences for a given time period (i.e., leading session).
 Cannot able to detect ranking fraud happened in
Apps’ historical leading sessions
 There is no existing benchmark to decide which
leading sessions or Apps really contain ranking fraud.
Proposed System
 we first propose to accurately locate the ranking fraud by
mining the active periods, namely leading sessions, of mobile
Apps.
 we propose an optimization based aggregation method to
integrate all the evidences for fraud detection.
 we evaluate the proposed system with real-world App data
collected from the iOS App Store for a long time period.
Advantages
 The proposed framework is scalable and can be
extended with other domain generated evidences for
ranking fraud detection.
 Experimental results show the effectiveness of the
proposed system, the scalability of the detection
algorithm as well as some regularity of ranking fraud
activities.
 we develop four intuitive baselines and invite five
human evaluators to validate the effectiveness of our
approach Evidence Aggregation based Ranking
Fraud Detection (EA-RFD).
Hardware Requirements
 System : Pentium IV 2.4 GHz.
 Hard Disk : 80 GB and above
 Ram : 512 MB and above.
Software Requirements
 Operating system : Windows XP/7.
 Coding Language : JAVA/J2EE
 IDE : Netbeans 7.4
 Database : MYSQL
THANK YOU

You might also like