Improving Click Fraud Detection by Real Time Data Fusion

Kantardzic, Mehmed; Walgampaya, Chamila; Wenerstrom, Brent; Lozitskiy, Oleksandr; Higgins, Shana; King, David C.

doi:10.1109/isspit.2008.4775655

Cited by 13 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…New features have to be created using existing parameters to capture the behavior of the partners. Previous studies [2,3] show that these fraud partners try to act rationally when simulating clicking behavior. However, despite (or perhaps due to) these endeavors, their click pattern still deviate from the typical click patterns of legitimate partners.…”

Section: Introductionmentioning

confidence: 99%

A Novel Ensemble Learning-Based Approach for Click Fraud Detection in Mobile Advertising

Perera¹,

Neupane²,

Faisal

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. By diverting funds away from legitimate partners (a.k.a publishers), click fraud represents a serious drain on advertising budgets and can seriously harm the viability of the internet advertising market. As such, fraud detection algorithms which can identify fraudulent behavior based on user click patterns are extremely valuable. Based on the BuzzCity dataset, we propose a novel approach for click fraud detection which is based on a set of new features derived from existing attributes. The proposed model is evaluated in terms of the resulting precision, recall and the area under the ROC curve. A final ensemble model based on 6 different learning algorithms proved to be stable with respect to all 3 performance indicators. Our final model shows improved results on training, validation and test datasets, thus demonstrating its generalizability to different datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Ensemble Learning-Based Approach for Click Fraud Detection in Mobile Advertising

Perera¹,

Neupane²,

Faisal

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In each of these modules, output is a probabilistic measure of evidence for the click being fraudulent. Authors have discussed the functionality of each of these modules in detail before [Kantardzic et al, 2008]. …”

Section: Fusion Of Evidences Of Click Fraud In the Ccfdp Systemmentioning

confidence: 99%

“…17. The dataset was used in t he rule based module alone and found t hat the average 53% of t raffic is suspicious [Kantardzic et al , 2008]. \iVhen running t he out lier detection module alone on t he dataset we discovered t hat about 34.6% of all clicks had one or more attributes t hat were found to have an outlying attribute-value pair count .…”

Section: Comparison Of Improvements In Quality Of Trafficmentioning

confidence: 99%

“…It was first detected and reported by the Netl\Iosaics click fraud detection system in 2010 [Kantardzic et al, 2008, Kantardzic et al, 2010a. Smart ClickBot is a for-sale click bot and it can be purchased [Walgampaya and Kantardzic, 2010j.…”

Section: An Overview Of the Smart Clickbotmentioning

confidence: 99%

“…Fraudulent clicks arc recognized by machine learning algorithms, which use information regarding the navigational behavior of users to try and distinguish between human and robot generated clicks [Immorlica et a1., 2005]. Such algorithms are mainly built using rule based techniques and most of them are classification systems [Metwally et a1., 2005a], even though a few score based systems are also reported [Ge and Kantardzic, 2006, Kantardzic et al, 2008, Kantardzic et a1., 2009. Most of the click fraud solution providers, including search engines and third party solution providers, claim their rule-based expert system is the best among the others taking the advantage of keeping "rules" as a secret weapon.…”

Section: Modeling Of Knowledge and Validationmentioning

confidence: 99%

See 2 more Smart Citations