Assessment of the Impact of COVID-19 on Grocery Retail in Ukraine
Abstract
The coronavirus crisis affected the development of the global financial system: for some industries, the impact was extremely negative, reducing the market value of specific companies by more than 50%. However, the effect of the crisis on non-cyclical industries such as retail is not easy to assess. The resilience of companies strongly depends on the flexibility and multi-format qualities of the business model and the ability to innovate. For specific market players, the crisis period has become a window of opportunity to increase market share. For grocery retail in Ukraine, enormous challenges driven by COVID-19 influenced the acceleration of the transition from traditional sales channels to online shopping and led to an unexpected sharp growth of convenience and hard-discount store sectors. Consumers had to learn to live with the new reality that changed their shopping behaviors; a large proportion of them started to shop for groceries via online channels that they had never used before. A significant number of consumers are going to stick to online channels even after the reopening of brick-and-mortar stores. The objective of this research was to explore how COVID-19 affected the dynamics of the grocery retail market using economic-mathematical modeling. In employing Machine Learning methods, the authors offered an approach to assess the effects of the restrictions that the Ukrainian government imposed to localize the spread of COVID-19. The effects on consumer behavior metrics were modeled and interpreted according to local retailers’ business models, the location qualities of brickand-mortar stores, and potential shifts towards digital sales channels in specific regions.
Keywords: COVID-19 economic effect, grocery retail, consumer behavior, digital transformation
References
[1] World Bank database: World development indicators [Internet]. World Bank; 2020 [cited 2021 Apr 1]. Available from: https://databank.worldbank.org/source/world-development-indicators
[2] Verstyuk I. Restoration in Ukrainian. How the country’s economy surprised the world by surviving the Corona crisis, and how it will grow in 2021 [Internet]. Novoye Vremya. 2021;7 [cited 2021 Apr 1]. Available from: https://biz.nv.ua/ukr/economics/ekonomika-ukrajini-u-2021-roci-prognozi-vplivpandemiji-pidsumki-2020-roku-novini-ukrajini-50144128.html
[3] Gross domestic product (in constant prices) [Internet]. State Statistics Service of Ukraine; 2020 [cited 2021 Apr 1]. Available from: http://www.ukrstat.gov.ua/
[4] McKinsey & Company. Perspectives on retail and consumer goods [Internet]. McKinsey & Company; 2020 Aug. No.: 8. Available from: https: //www.mckinsey.com/${\sim}$/media/McKinsey/Industries/Retail/Our{%}20Insights/ Perspectives{%}20on{%}20retail{%}20and{%}20consumer{%}20goods{%}20Number{%}208/ Perspectives-on-Retail-and-Consumer-Goods_Issue-8.pdf
[5] Deloitte. Consumer sentiment of Ukrainians in 2020. Industry group for retail and wholesale distribution [Internet]. Deloitte; 2021. Available from: https://www2.deloitte.com/content/dam/Deloitte/ ua/Documents/Press-release/RWD{%}202020{%}20UA.pdf
[6] Zielke S. How price image dimensions influence shopping intentions for different store formats. European Journal of Marketing. 2010;44(6):748-770.
[7] Lakshay A. An awesome tutorial to learn outlier detection in Python using PyOD Library [Internet]. Analytics Vidhya; 2019 Feb 14 [cited 2021 Apr 1]. Available from: https://www.analyticsvidhya.com/blog/ 2019/02/outlier-detection-python-pyod
[8] Harvey A, Peters S. Estimation procedures for structural time series models. Journal of Forecasting. 1990;9:89–108.
[9] Taylor SJ, Letham B. Forecasting at scale. The American Statistician. 2018;72(1):37–45.
[10] Harvey A, Shephard N. Structural time series models. Handbook of Statistics. 1993;11(10):261–302.
[11] Carpenter B, Gelman A, Hoffman MD, et al. Stan: A probabilistic programming language. Journal of Statistical Software. 2017;76(1):1-32. https://doi.org/10.18637/jss.v076.i01s