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

Abstract

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.

Gradient boosting learning for fraudulent publisher detection in online advertising

“…The author has employed random forest (RF) with up/ down sampling for discriminating the status of the publishers as fraudulent, genuine or under observation. (Perera et al, 2013) proposed an approach for detecting click fraud in online advertising using the ensemble methods. They designed 41 new features extracted from the existing attributes and employed these features for modeling suspicious conduct of the publisher.…”

User click fraud detection method based on Top-Rank-k frequent pattern mining

“…The click times of data under different time complexity and students' evaluation information are obtained by marking targets, and the click frequency, real evaluation score, click stream density of users are compared. Compared with traditional frequent pattern mining algorithm, behavior feature selection algorithm, 26 web mining algorithm, etc., 27 as shown in Table 1, the proposed algorithm is generally better than the other three.…”

E-Mail Spam Filtering: A Review of Techniques and Trends

“…by a virus/Trojan infection or by a specific bot software), can be used to send out spam or malware, harvest password and login information for identity theft and fraud, re-route users to spoofed websites, or even recruit new bots, and so on. Botnets on the other hand constitute a major threat to the Internet infrastructure as they have the capability to -mount crippling denial of service (DoS) attacks on servers, generate click-fraud [Perera et al, 2013], send out a flood of spam and backscatter [Xie et al, 2008] facilitate phishing and pump-and-dump schemes, form a computational grid to break weak passwords or obfuscate the operators point of origin, etc. Botnets run on the global level outside the range of national boundaries.…”