Fraud Detection through Graph-Based User Behavior Modeling

Student: Streltsov Anton

Educational Programme: Data Science (Master)

Year of Graduation: 2020

Modern society is highly dependable on the Internet. In recent years awareness about fake and misguiding information has been raised. Many web-platforms have implemented active policies against authors that generate such content. Although the problem is as old as the Internet itself, current advances in the data analysis domain can lead to the new outcomes in the task of the user clusterization that is essential as the part of fraud detection techniques. This work studies recently developed methods in pattern mining via deep convolutional autoencoder models. These methods are studied in the context of fraud detection through classic graph-based approaches as a part of link mining procedure. This work implements end-to-end system of fraud clusters detection in order to evaluate proposed methods on real data.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses