Fraud Detection of AD Clicks Using Machine Learning Techniques

Abstract

Although all businesses face the possibility of fraud, those that rely on internet advertising face an especially high risk of click fraud, which may lead to inaccurate click statistics and unnecessary expenditures. The cost per click for advertising channels might skyrocket if enough people click on the ads. Internet advertising is becoming a significant revenue source for many websites. Under this model, advertisers pay the publisher a flat rate for each click-through from the ad to the advertiser's site. Since spending much on Internet advertising requires significant resources, the term "click fraud" refers to an attack tactic in which the perpetrator repeatedly clicks on a single link for the sole purpose of generating illicit revenue. By clicking on a pay-per-click (PPC) ad many times using a script, fraudsters may trick online advertisers into paying for clicks that never happened. We may use a variety of methods to identify click fraud anytime a human or computer program clicks on a particular link, and then use the click-through rate to ascertain whether the clicker is legitimate. This work provides a machine-learning strategy for predicting user click fraud, which will enable us to distinguish between fraudulent and legitimate clicks and, therefore, identify fraudulent users from legitimate ones. We have used KNN, SVC, and Random Forest models for this purpose.