• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
For visually-impairedUser profile (HSE staff only)SearchMenu

Implementing Machine Learning for Food Retail Sales Forecasting

Student: Mikhail Kondrashov

Supervisor:

Faculty: St. Petersburg School of Physics, Mathematics, and Computer Science

Educational Programme: Big Data Analysis for Business, Economy, and Society (Master)

Year of Graduation: 2021

Retail refers to a business sphere to sell goods and services to the end-consumers for personal consumption. Sales forecasting is one of the most challenging and crucial tasks since accurate sales forecast plays a major role in the whole chain profitability. In this paper, we develop the gravity model for potential conventional stores openings for one of the largest Russian retailers. The company’s internal database, consisting of 1,420 variables, was used to train the Random Forest model with the Gradient Boosting technique. The database includes competitive and infrastructural environment characteristics, information about the population and its financial sustainability. As a result, we delivered the average forecast accuracy of 86% which significantly outperforms an analog method, previously used to forecast sales of the potential stores. Moreover, we included Shapley algorithm that allows estimating input of the explanatory variables both on each prediction and whole model level. Nowadays the designed model is actively implemented into the company’s operations as the main provider of forecasts for potential openings.

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