Fraudulent Users Detection on Social Media Platforms Using Machine Learning Techniques

Abstract

The social network, a crucial part of our life is plagued by online impersonation and fake accounts. In this project, a model is trained such that it could be used to classify a social media account as fake or genuine. This model uses Support Vector Machine and Deep Neural Network as a classification technique and can deal with a huge dataset of records immediately, taking out the need to assess each record physically. The primary concern to us here is Fake Accounts which are to be identified and so our problem can be said to be a classification or a clustering problem. As, this is an automatic detection method, it can be applied easily by online social networks which has millions of profiles, whose profiles cannot be examined manually.