Detecting Click Fraud Using an Improved Lenet-5 Convolution Neural Network

Abstract

Online advertising has grown drastically over the last couple of decades by making billions worth of business markets all over the world. Click Fraud can be identified as one of the common malpractices when it comes to digital platforms. This leads to an increase in the revenue of the Ad publishers and huge losses for the advertisers. Hence the need of detecting click fraud has become a major concern in online marketing. Recent studies have proposed different kinds of machine learning based approaches to detect these fraud activities. In this study, we propose an improved Lenet-5 Convolution Neural Network to identify click fraud. This proposed novel deep learning algorithm was able to achieve an accuracy of 99.09% by using deep features of the proposed Lenet-5 based Convolution Neural Network.