• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Daniil Baryshev
Deployments Risk Modeling
Data Science
(Master’s programme)
2019
In this paper, we consider the problem of forecasting the number of requests from users for errors in the functional information systems of VTB Bank (PJSC), which carried out the introduction of new improvements or bug fixes. This indicator determines how efficiently and timely the installation was performed. In the course of the study, two models were constructed using different methods of evaluation and optimization. The results of the model based on a combination of optimizers are estimated as close to real. The results of the model based on the neural network are estimated as sufficient. The obtained forecasting tools are designed to solve one of the topical problems of support and development of banking systems - reducing the number of errors after the implementation of improvements. The paper identifies two approaches to the use of simulation results - actions before implementation and actions upon installation. As an example of pre-installation actions, we can cite the strengthening of testing of the specified functionality, changing the composition of the implementation or changing the installation date. Taking the forecast as a given, support units can pre-allocate human resources in case of large bursts of appeals.

Optimization of implementation is one of the leading areas in VTB Bank. By improving the ways of making functional changes to the Bank's productive systems and reducing the impact of such implementations, the Bank improves two main aspects of its activities - providing the market with modern, convenient and efficient functionality covering all financial transactions, and improving its reputation. This work is the basis for the construction of a Bank-wide model for assessing the quality and impact of implementation. The inclusion in the model of performance indicators of other banking systems and other factors, such as statistics testing improvements or categorization of improvements by business processes, is the next step in the development of this study.

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