Retail Demand Forecasting Model Improvement in Data-limited Environment

Student: Surtaeva Mariya

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

The topic of this paper is "Retail Demand Forecasting Model Improvement in Data-limited Environment". The volume of work is 59 pages and includes 7 tables and 15 figures, 34 sources were used. The object of the research is sales data of a Russian digital retailer. The subject of the research is demand forecasting models. Purpose of work: improving the quality of the sales forecasting model using information about the product. As a result of the work, a new way of accounting for the availability of goods in the past was developed and applied, as well as gradient boosting models were studied and built. Measurement of quality metrics of the models showed that foreacast was improved with the new methods and expansion of the dataset. The most efficient and sustainable model is used in the company and enhance demand prediction.

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