One of Russia’s largest retail chain drives expansion using analytics

Home - Case Studies - One of Russia’s largest retail chain drives expansion using analytics

Latest Posts

Tags Cloud

In the ultra-competitive retail sector, traditional sources of decision-making – such as sales history, and executives’ experience and intuition – are now insufficient. The client with its high growth, distinctive hypermarket model wanted to understand how they could help themselves with the decade long historical data collected over the years.

Algoscale left no stone unturned in extracting & providing actionable insights and empowered the client to make strategic decisions like finding the sweet spot for setting up new stores to drive group’s expansion.

The Client

Founded in 1993 in St. Petersburg, Russia, the client is one of the largest retail chains in Russia and the country’s one of the largest hypermarket chain. It operates 233 hypermarkets in 84 cities across Russia and 113 supermarkets in Moscow, St. Petersburg, Novosibirsk, Yekaterinburg and the Central region with a total of approximately 1,402,428m2 of selling space.

The Challenge

Enormous size of data in an unstructured format for over a decade was lying unused in spreadsheets and has never been leveraged for gaining business insights. The client wanted to take strategic decisions on setting up new stores based on insights from existing data. One of the major challenges was that large volume of data in inconsistent format. Multiple variables like store name, store code, retailer name, store format, geographical location, purchase transactions per store, total store sales and sub-categories like product type, description, brand product code, customer loyalty program, demographics etc. added to the complexity making any manual treatment unsuitable. Further, the project was to be delivered within stringent timelines.

The Solution

Algoscale provided a simplistic yet detail oriented, data driven analysis. As millions of customers make millions of purchases, every day, every hour, different types and degrees of data which is evidently cluttered and scattered needs to be processed step wise. We began by screening each and every available variable/ factor and applied advanced excel analysis to clean & format the disparate and siloed data provided to us by the client. Using shell scripting the final data was prepared in order to be used for generating variety of reports such as summary of customer behavior by catchment incorporating declining customers’heatmap, average sales and customer sales trend. All these reports generated were integrated in a separate customized web dashboard with the help of Business Intelligence (BI) tools.

Benefits

The analysis aided the client to decide where the new stores should be opened based on intelligence drawn about the competitors and according to the customer demand. Heatmaps of the catchment area provided the necessary details clearly and specifically so as to where the customers were declining and where there is possibility of finding new customers. The client concluded that they needed to improve the customer experience at some stores and as well as open the stores in upcoming cities where they had no stores and competitors were not able to arrest attrition of their customers.

Technology Stack

Kibana & ElasticSearch.

Leave A Comment