T. Namrata1 T. Ranga Rao2 Briskilal J.
3 (M. E.)B. Tech.
) B. Tech. (C.S.E.) Assistant ProfessorSRMInstitute of Technology SRM Institute of Technology SRM Institute of Technology AbstractApps downloaded by users aremostly based on the psyche of downloading well-rounded and efficiently workingapps. These performance parameters are assessed by the general users by ratingthese apps on a scale of 5.
The top rated apps are the first to appear whilesearching and sorting for the desired apps. However, these ratings are beingtweaked and fraudulently misrepresented to appear on the popularity lists toboost downloads. There is a collective nod among the users to keep thesedubious deeds of misrepresentation at check. This fraudulent representation ofmobile app ratings will be discerned in this paper by detecting the leadingsessions of the App at which the fraudulent ratings are depicted. Secondly,rating, ranking and review based evidences are mined by modelling Apps’behaviours of the same using statistical hypothesis tests. Furthermore, all theevidences for the detection of the fraud are integrated by optimization basedaggregation method. The efficacy and the scalability of the detection algorithmand the proposed system are validates by implementing the same on real-lifedata of the Apps collected from iOS App Store.
Keywords: ranking frauddetection; ranking based evidence; rating based evidence; review basedevidence; evidence aggregation. IntroductionWith the advent of the wide spread practice of cellular mobiles withinternet connectivity that replaced the public switch telephone network (PSTN),the face of the functioning of humans across the globe has taken giant leapstowards advancements in the fields of communication and connectivity. Mobileapplications have become the lifelines of these very smart phones with internetaccess through mobile broadband. In 2008, the App Store released by Apple gavea drastic turn to how smartphones are used altogether with the intent ofwell-packages, downloadable apps on phones.
Since then, the mobile applicationmarket has exponentially multiplied faster than a beanstalk. With projectedgross annual revenue to surpass $189 billion by the year 2020, the populationof web developers has seen a huge rise in numbers. With so much collectiveenthusiasm in this field, the number of mobile applications in the play storehas shot up with fierce competitions among the app developers for higher numberof downloads. Like in any field, the bug of fraudulent projections ofperformances has bitten this domain as well with fake representation of toprankings of Apps by some App developers which dupes users into downloadingtheir Apps.
The fake top leader board positions are achieved by paying up for abot farm or human/internet water armies that are hired to rate, rank andprovide the said App with a better review. Quite significantly, with 6.2billion app downloads in India in 2016, about 16.2% of the downloads showedsome kind of fraud with India ranking 10th highest ranking countryfor app install fraud rate by Tune’s Accounting. Thus, this must be controlledto provide the users with an authentic list of Apps for them to choose from andgive a fair chance to the Apps that genuinely appear on top of the App leaderboards. To curtail this fraud, the proposed system detects ranking frauds thatoccur majorly during the leading sessions of the Apps and not throughout thelifecycle of the Apps. Leading sessions of the App lifecycle have the highestprobability of a red flag being noticed in the ratings.
Thus these leadingsessions must be detected in the first module. Once, the leading sessions aretracked, the rating based evidences, ranking based evidences and the reviewbased evidences are extracted from the modelling Apps’ behaviours of rating,ranking and reviews by making use of statistics hypothesis tests. Theseevidences will be aggregated using aggregation methods based on optimization.If the said evidences differ vastly from the historical performances of Apps interms of ratings, rankings and reviews, then there is an anomaly that must beaddressed for course correction in the App rankings.
LiteratureSurvey: Severalpapers were reviewed to make the paper comprehensive for further research. Thereare majorly three categories into which the research work can be grouped into. Firstly, web ranking spam detection detectsany incidence of web spamming. Web spamming is the procedure of raisingparticular web pages by tweaking page ranking algorithms of search engines. A,Ntoulas presented a range of heuristic methods to detect factors affecting spamon web based on content to find heuristic methods. Using spamicity, Zhou et al.proposed online link spam and spam detection methods.
Secondly,online review spam detection: B. Spirin et al. did a survey that introducedmany algorithms and principles in literation for Web Spam Detection. 3 Thirdly,Mobile App Recommendation: it lays emphasis on the algorithms and factorsaffecting them in recommending mobile application to users in ways of usingtarget marketing. Aflexible generative model for preference aggregation authored by M. N.
Volkovs and R. Zemel has expressed a model that proposes a malleable model overcomparisons where preferences to items could be conveyed in different formsthat otherwise make the aggregationproblem hard. Several experiments done on high yardstick datasets state higherperformance compared to existent methods.
Unsupervisedrank Aggregation with domain-specific expertise proposed by A. KKlemetiev, D.Roth, K. Small and I.
Titov have suggested a framework for learning toaggregate rankings with domain specificexpertise sans supervision by applying it to the sceneries of combining fullrankings and aggregating top-k lists, indicating major progress overdomain-agnostic standard in these cases.These arethe sources of literature based on which the proposed system was articulatedand presented. 1.
Ranking Detectionand Avoidance Frauds in Mobile Apps Store9 Author/citation Objective Key findings Limitations ABHIILASH T P, L DINESHA Detecting and avoiding ranking frauds in mobile applications Experiene based evidences Review based evidences could be taken into consideration as well. 2. Fraud Application Detection Using DataMining Techniques 11 Author/citation Objective Key findings Limitations Tejaswini Shingare , Madhuri Sancheti, Swaleha Shaikh, Jyoti Ugale, Prof.
J.N.Kale Detecting ranking frauds in mobile applications Boolean weight as 0 or 1 is assigned to every evidence where no fraud is indicated by 0 and fraud is indicated by 1. Fraud usually occurs in the leading sessions of the apps lifecycle which is not mined for. 3.
Discovery of Ranking Fraud for Mobile Apps 14 Author/citation Objective Key findings Limitations E. Ramya,. V. Vetriselvi Identifying ranking frauds in mobile apps a positioning extortion discovery framework for mobile Apps Ideal bond between ranking, rating and survey evidences can be established. 4. Discovery of Ranking of Fraud for MobileApps Author/citation Objective Key findings Limitations Ranjitha.
R, Mathumitha.K, Meena.S, S.
Hariharan Detecting fraudulent ranking in mobile applications an optimized admin verification method to evaluate the reliability of leading sessions of mobile Applications Aggregation of the evidences could lead to a collective understanding of the fraud. Challenges Faced:Identifyingfraud ranking for Apps is a subject still under study. We propose a system tofill the void a little in detecting this fraud. There are a certain challengesthat we face on doing so that are listed below.
Firstchallenge, the ranking fraud does not occur all the time in the lifecycle of anApp. Hence, we need to detect the time when it happens leading to identifyinglocal anomaly instead of global anomaly. Second challenge is to possess scalability detectranking fraud certainly without the use of any basis information because manuallabelling of ranking fraud for each and every App is very difficult. Finally,it is hard to catch and verify the evidences associated with ranking fraud dueto the volatile nature of rankings in the charts, which influences us todiscover contained fraud patterns of mobile Apps as evidences. Overviewof the Proposed System System Proposed: We have proposed a simple algorithm with good efficacy to detectleading sessions of each App based upon its’ historical records. It isdiscovered that fraudulent Apps have their ratings spiked during the leadingsessions by analysing their ranking behaviours.
By examining the rankingbehaviours of Apps, we notice that the fraudulent Apps habitually havedifferent ranking patterns in each leading session likened with normalApplications. Furthermore, grounded on Apps’ past records of rating and review, twokinds of fraud evidences are gathered. Any anomaly detected will flag the redflags for fraud detection.
The time period of popularity for an App isreflected by its leading sessions. Thus, ranking fraud scenarios can be foundedby identifying susceptible leading sessions. Also, the major work here involvesextraction of leading sessions from the Apps’ historical records of ranking.The two main segments of fraudulent ranking detection are as follows:o Detecting mobile apps’ leading sessions.
o Detecting evidences that support ranking frauddetectionTo have a brief look at these aspects, 1) Detecting mobile apps’ leading sessions.This in turn is divided into two segments. Firstly, the leading eventsare extracted from the Apps past records of ranking. Secondly, leading sessionsare erected by merging the leading events together. An algorithm identifiesleading events and sessions by skimming the historical records of the App frompseudo code for mining sessions of a certain mobile app.
2) Detecting evidences that support ranking fraud detection.There are three types of evidences that support the detection offraudulent ranking. a)Evidence based on Ranking: The leading sessions comprise of theleading events which can be analysed of their general behaviours for an anomalywith the app’ past records of the same. It is observed that a certain patternof ranking is always fulfilled by ranking behaviour of the app in case of aleading event. b) Evidence based on Rating: The previous evidence is helpful but notadequate for conclusion of results.
To restrict the problem of “restrict timedepletion”, evidence accumulation is also based on historical records of ratingfor mobile apps. Since the rating is done after an app is installed by theuser, the higher the rating the higher its position in the leader board whichwould result in further downloads by attracting new users. Naturally, ratingfraud occurs during the leading sessions in the case of an anomaly which can beused to identify evidence for fraudulent rating of the mobile apps. 3) Evidence based on Review:Review contain textual comments on the app and its performance.
These reviewsare given by current users of the app who have already installed the said app.This can be termed as the hardest segment of evidence that can be gathered. These are compared again with the apps’historical record of reviews and if there is an unusual spike of good reviewsduring the leading sessions, evidence is said to be gathered. The above mentioned three evidences are merged using evidenceaggregation technique that is unsupervised. This helps test the integrity ofmobile Apps’ leading sessions.
The statistical hypotheses tests models Apps’ranking, rating and review behaviors to extract all the evidences. This outlineis scalable which can be drawn-out with other area spawned evidences fordetecting ranking fraud. At last, the proposed system will be tested withreal-world data of Apps composed from Apple’s App store for a time extent ofmore than two years. Deduction: This paper reviews variousexisting methods used for web spam detection, which is related to the rankingfraud for mobile Apps. Also, we have seen references for online review spamdetection and mobile App recommendation. By mining the leading sessions ofmobile Apps, we aim to locate the ranking fraud.
The leading sessions works fordetecting the local anomaly of App rankings. The system aims to detect theranking frauds based on three types of evidences, such as ranking basedevidences, rating based evidences and review based evidences. Further, an optimization based aggregation methodcombines all the three evidences to detect the fraud. References: 1https://en.wikipedia.
Ge,H. Xiong, C. Liu, and Z.-H.
Zhou. “A taxi driving fraud detection system” InProceedings of the 2011 IEEE 11th International Conference on Data Mining, ICDM’11, pages 181–190, 2011 8 Hengshu Zhu, Hui Xiong, Senior Member,IEEE, Yong Ge, and Enhong Chen, Senior Member, IEEE “Discovery of Ranking Fraudfor Mobile Apps” IEEE Transactions On Knowledge And Data Engineering, Vol. 27,No. 1, January 2015.9 ABHIILASHT P, L DINESHA “Ranking Detection and Avoidance Frauds in Mobile Apps Store” 1stInternational Conference on Innovations in Computing & Networking(ICICN16), CSE, RRCE10 MonaliZende & Prof.Aruna Gupta “Ranking Fraud and Fake Reviews Detection forMobile Apps”International Journal of Advanced Research in Computer Science,201611 TejaswiniShingare, Madhuri Sancheti, Swaleha Shaikh, Jyoti Ugale, Prof.J.
N.Kale “Fraud ApplicationDetection Using Data Mining Techniques”, IJARIIE, Vol-3 Issue-2 201712 Ranjitha.R,Mathumitha.K, Meena.
S, S.Hariharan, “Discovery of Ranking of Fraud for MobileApps”, (IJIREM), Volume-3, Issue-3, May-201613 Ms.Prajakta U. Gayke , Prof. Sanjay B. Thakare, “”Ranking Fraud Detection forMobile Apps using Evidence Aggregation Method, IJEDR Volume 4, Issue 3,2016.
14 E.Ramya Mrs. V. Vetriselvi,” Discovery of Ranking Fraud for Mobile Apps”002C IJSTE- Volume 2, Issue 12,June 2016.
15 Mrs. CHAPPORVA, 2Mr. K.ASHOK KUMAR,” Discovery of ranking fraud for Mobile Apps”,IJCERT, Volume 3, Issue 6, June-2016.