Forecasting Customer Lifetime Value through Machine Learning and Time Series Analysis of Banking Product Transactional Data

Student: Ekaterina Ivanchenko

Supervisor: Margarita Burova

Educational Programme: Master of Data Science (Master)

Year of Graduation: 2024

Predicting Customer Lifetime Value (LTV) allows companies to optimize marketing strategies, target resources on the most valuable customers, and identify product issues at early stages. This study investigated various machine learning and time series tools applied to data from a Russian bank, collected from over 21,000 clients during the period from August 1, 2023, to January 31, 2024, focusing on the payment sticker product. The objective of the study was to train several time series models for forecasting Customer Lifetime Value and select the best one. As a result, seven time series models were trained and their performance was compared using MAE and RMSE metrics. The best result, with MAE = 0.099 and RMSE = 0.151, was achieved by the deep neural network model RNN (GRU).

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