Classification of Clients on Fraudsters and Legitimate Clients Using Transactional History

Student: Mansurov Konstantin

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Final Grade: 7

Year of Graduation: 2019

Fraud detection is one of the banking problems that can be solved using machine learning. This task contains several problems that were solved in this work. To deal with the imbalance of data, the oversampling technique - SMOTE, as well as the undersampling method - RandomUnderSampling, was applied. LogisticRegression, RandomForest and XGBoost were selected as classifiers. The main purpose of this research is - to make a fraud classification algorithm that will complement the existing Sberbank algorithm.

Full text (added May 26, 2019)

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