MULTIFACTOR REGRESSION ANALYSIS AND FMCG RETAIL SALES FORECASTING IN OFFLINE STORES USING POS DATA

Abstract

In the modern retail trade companies-producers and suppliers use a variety of ways to promote their products due to high competition among FMCG products. At the same time, the level of data collection and storage technology allows for the accumulation of POS data across a broad range of metrics, including those that reflect sales growth efforts and the results of these efforts. Every retail outlet becomes a source of invaluable POS data. The use of POS data has not yet become a common practice, but interest in this source is constantly growing. The article examines the use of POS data to estimate the level of specific factors influence on FMCG sales in retail outlets. Regression analysis is carried out basing on such POS data as the product price, the total distribution point, the shelf share, on-shelf availability, the product stock level. The obtained regression equations are analyzed in terms of their economic sense and practical application. It is concluded that at a certain stage of development of the product line or brand the producing company should focus on that particular type of promotion, whose high level of influence becomes evident from the regression equation. This promotes the data-driven decision making and improves the efficiency of business processes. The possibility of using regression analysis with POS data as explanatory variables for sales forecasting is also discussed, since the price and the level of representation in the store largely determine the demand for FMCG products, which means they will be good predictors for the forecast.

Keywords: correlation analysis, sales forecasting, regression analysis, retail trade, FMCG, POS data

References

• Kotler Ph. According to Kotler: The World's Foremost Authority on Marketing Answers Your Questions. AMACOM, 2005. 168 p.
• Dobrohotov A.V., Volynskyi V.U. Sovremennoe sostoyanie metodologii prognozirovania obyomov prodazh gotovoi produkcii [Current state of the methodology for forecasting sales volumes of finished products // A Collection of Scientific Works of Russian Universities "Problems of Economy, Finance and Production Management". 2010. Vol. 29. Pp. 192-201. (In).
• Shanin I.I., Ataekgaev Y.B. Methods of Forecasting of Sales Volumes of Production // European Student Scientific Journal. 2018. Vol. 2. Pp. 45. (In Russ.).
• Armstrong D.S. Prognozirovanie prodazh [Sales forecasting]. Marketing. SPb.: Piter, 2002. Pp. 351-368. (In Russ.).
• Mkhitaryan S.V., Danchenok L.A. Sales Forecast Using Adaptive Statistical Methods // Fundamental Research. 2014. Vol. 9-4. Pp. 818-822. (In Russ.).
• Yushin A.A. Sales Forecasting for Furniture Products // Bulletin of the Volga State University of Service. Series: Economy. 2015. Vol. 1(39). Pp. 148-155. (In Russ.).
• Karlov A.M., Nevrotov L.K. Using the Method of Correlation and Regression Analysis in Forecasting of Sales on the Example of the Food Industry in the Region // Baltic Economic Journal. 2019.  2(26).  Pp. 100-107. (In Russ.).
• Rebenok I.I., Malykhina M.P. Data Mining Methods and Forecasting Data in Fixed Retail Chain // Modern Problems of Science and Education. 2014. 3.  Pp. 151. (In Russ.).
• Mou S., Davia D.R., Nicole D. Retail Store Operations: Literature Review and Research Directions // European Journal of Operational Research. 2017. Vol. 265(2). Pp.399-422. DOI: 10.1016/j.ejor.2017.07.003
• Sajawal M., Usman S., Sanad A.H., Hayat A., Ashraf M.U. A Predictive Analysis of Retail Sales Forecasting using Machine Learning Techniques // Lahore Garrison University Research Journal of Computer Science and Information Technology. 2022. Vol. 6(04). Pp. 33-45. DOI:54692/lgurjcsit.2022.0604399
• Jain A., Menon M.N., Chandra S. Sales Forecasting for Retail Chains // San Diego, California: UC San Diego Jacobs School of Engineering.
• Odegua R. Applied Machine Learning for Supermarket Sales prediction //Project: Predictive Machine Learning in Industry.
• Anna-Lena B., Stefan M. Safety Stock Planning under Causal Demand Forecasting // International Journal of Production Economics. 2012. Vol. 140(2). Pp. 637-645. DOI: 10.1016/j.ijpe.2011.04.017
• Paul F., Neil B., Phillip E.P., David J.R. Marketing Metrics the Manager’s Guide to Measuring Marketing Performance. Third edition. Publisher: Pearson, 2016. 427 p. (In Russ.).
• Peter B., Andrew B., Peter G. Practical Statistics for Data Scientists 2nd edition. Publisher: O’Reilly, 2020. 360 p.
• Andrew G., Jennifer H., Aki V. Regression and Other Stories. Publisher: Cambridge University Press, 2020. 548 p. (In Russ.).

About the Author

Yulia V. Napolskaya – Business Analyst, Procter and Gamble, Moscow, Russia. E-mail: jnapolskaya@gmail.com. SPIN РИНЦ 8536-2940. ORCID 0009-0009-6072-4581. Researcher ID KTI-2986-2024

For citation: Napolskaya Y.V. Multifactor Regression Analysis and FMCG Retail Sales Forecasting in Offline Stores Using             POS data // Beneficium. 2024. Vol. 4(53). Pp. 49-57. (In Russ.). DOI: 10.34680/BENEFICIUM.2024.4(53).49-57