Prediction of Client's Response Based on Machine Learning Techniques

Student: Khodyreva Viktoriia

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2017

Banks and other financial institutions face a problem of identifying the clients who are likely to purchase a campaigned product, based upon the socio-demographic, financial information, behavioral history and other data available. This is a binary classification problem that can be solved using different machine learning techniques. The aim of this work was to apply and compare the performance of several methods including the Logistic Regression, Neural Network, Random Forest, Gradient Boosting on real data from one of the Russian banks. The process of modelling included data gathering and preprocessing, feature selection, tuning model hyperparameters and evaluation of model performance. The best model based on the ROC criterion was the Gradient Tree Boosting model.

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