N.N. Babikova1, M.A. Osipov2

1,2 Pitirim Sorokin Syktyvkar State University (Syktyvkar, Russia)
1 valmasha@mail.ru, 2 osipov.ma13@gmail.com

When choosing a location for new business facilities, there is an urgent problem related to the objective assessment of potential customer traffic and the choice of the most profitable location. It is necessary that the decision-making process be based on the analysis of current geodata, in particular the distribution of population density, to ensure maximum efficiency and profitability of the business.

To predict the customer flow based on data on Syktyvkar's population density and residential development characteristics using the Python programming language.

The most effective Python libraries are characterized and the main data sources for geo-analysis of the housing stock and forecasting customer traffic are analyzed; an algorithm for estimating the housing stock based on data on population density and characteristics of residential buildings with visualization of the results using a hexagonal grid, which is implemented using Python, is developed; the hypothesis about the influence of population density on customers is confirmed.-stomp; visualization of the results is presented to confirm the hypothesis.

The study provides businesses (primarily retail, banking, services, and real estate) with a practical Python-based geo-analytical tool for selecting optimal locations and predicting customer traffic based on population density data to make more accurate, profitable, and efficient decisions, increasing competitiveness and profitability in industries where location plays a role. a key role.

Babikova N.N., Osipov M.A. Using Python for geoanalytics: housing stock assessment and customer flow forecasting. Science Intensive Technologies. 2025. V. 26. № 4. P. 68–75. DOI: https://doi.org/ 10.18127/ j19998465-202504-08 (in Russian)

1. Saltanaeva E.A., Vasil'eva S.V., Eshelioglu R.I. Optimizaciya informacionnyh processov v oblasti marketingovyh issledovanij s primeneniem tekhnologij iskusstvennogo intellekta. Ekonomika. Informatika. 2024. T. 51. № 2. S. 413–424 (in Russian).
2. Grineva N.V., Topyrkin A.D. Geoanalitika: sbor, analiz i otobrazhenie geograficheskih dannyh dlya resheniya zadach razmeshcheniya kommercheskih organizacij. Innovacii i investicii. 2023. № 5. S. 296–302 (in Russian).
3. Lejfer L.A., Chernaya E.V. Massovaya ocenka ob"ektov nedvizhimosti na osnove tekhnologij mashinnogo obucheniya. Analiz tochnosti razlichnyh metodov na primere opredeleniya rynochnoj stoimosti kvartir. Imushchestvennye otnosheniya v Rossijskoj Federacii. 2020. № 3 (222). S. 32–42 (in Russian).
4. GeoPandas Documentation. URL: https://geopandas.org/ (data obrashcheniya: 12.12.2024).
5. Shapely Documentation. URL: https://shapely.readthedocs.io/ (data obrashcheniya: 24.12.2024).
6. Folium Documentation. URL: https://python-visualization.github.io/folium/ (data obrashcheniya: 17.12.2024).
7. Uber’s H3 Documentation. URL: https://h3geo.org/ (data obrashcheniya: 16.01.2025).
8. OpenStreetMap Data. URL: https://www.openstreetmap.org/ (data obrashcheniya: 18.01.2025).