• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Studies of Machine Learning Methods in Marketing and their Implementations in Banking

Student: Davydova Darya

Supervisor: Nikolay Kazantsev

Faculty: Graduate School of Business

Educational Programme: Business Informatics (Bachelor)

Year of Graduation: 2021

The digital transformation trend has impacted marketing in every industry. The introduction of machine learning technology allows you to solve problems such as personalization, predicting customer churn and predicting user behavior in general. This study is aimed at studying the application of machine methods in the banking sector, as well as in predicting the duration of a call to a client in a marketing campaign. In the theoretical part, the main technologies in marketing were considered. The work examines, in addition to machine learning, technologies such as chat bots, artificial intelligence, the Internet of Things, blockchain and automated marketing, as well as the use of these technologies in marketing in the banking sector. For the practical part, the sample was taken from a Portuguese study, which analyzed data from May 2008 to June 2013, providing information on calls from Portuguese retail bank customers who were asked to issue a term deposit. To select the best model for prediction, the following machine learning methods were compared: random forest, decision tree, regression and classification gradient boosting models, which showed the best result with a prediction accuracy of 75%. This article may be a supplement to other research opportunities using machine learning technologies in marketing, as well as using this technology in banking. The call duration forecasting model developed in this study can be used in the future, for example, to plan the time of a call, as well as to model the operator's text to provide a personalized approach to each client. However, since the data for 2008-2013 was used for the construction period of the model, today the situation may differ. In order to update the results of this study, a similar study should be carried out with a set of more modern data. It is also worth noting that the behavior of the client may differ depending on the services offered to him by the bank itself and the country in which he is located, therefore, research is needed on marketing campaigns for other services in different banks in different countries. Another area for future research is such telephone campaigns in additional areas such as insurance.

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