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

Implementation of Machine Learning Methods into Cloud Systems

Student: Filipyev Andrey

Supervisor: Andrey Dmitriev

Faculty: Graduate School of Business

Educational Programme: Big Data Systems (Master)

Year of Graduation: 2016

The aim of the graduation paper lies in the practical realization and the implementation of machine learning methods in the actual operating cloud system. Dodo IS is the cloud system that is being created to automate business processes of the company. This company works according to the system of the franchise sale that allows controlling all the main business processes. One of the most important modules is module of managing the work schedule of the employees. The module of work schedule of the employees has some predictable data that the sale outlet manager uses to set the time when an employee must work. One of the key figures, exactly the income, is counted with the help of very simple formula. The accuracy of this type of formula is rather low and more likely has a random character. This conclusion can be done by analysing the data, as in one case the accuracy may be lower than 10%, in others is close to 100% without any particular logic. The work carried out and described in this graduation paper is attempting to introduce machine learning methods into an information system that would allow us to improve the projected figures. The results of the research performed, we may say that the foundation was laid for the implementation of machine learning methods into the cloud system DodoIs. Firstly, the hypothesis of possibility of using the regression analyses with the data available was checked, and then the further directions were set for improving the quality of data model and forecasting results. Thanks to the developed forecasting module architecture we can say for certain that implemented module will suit all the requirements of working cloud system.

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