The group's shoppers find what they came for in stock more often, because demand is forecast store by store.
The group, with over 550 retail stores in 57 cities across 12 countries, wanted the right goods on its shelves in every region and its teams to act on one shared view of sales, stock and customers.
What changed
What stood in the way.
- Data on inventory, sales, customers and supply chain was split across departments, brands and regions.
- No one could see across regions or forecast demand accurately.
- 52%less manual effort (as reported)
- 65%faster reporting (as reported)
- 70%more data processing capacity (as reported)
What we built.
- A central data lake on Databricks on AWS, with PySpark pipelines processing 300GB of data a day and governance across regions.
- Custom APIs bringing in stock from SAP, daily sales from Dynamics 365, loyalty behaviour and footfall from Tyco sensors.
- Dashboards on desktop and mobile for stock movement, delivery, loyalty, conversions and gift cards, with checks on every data upload.
- Machine learning forecasting on sales history, seasons and regions, models that flag unusual sales and footfall, and Databricks Genie for questions in plain language.
- Databricks
- AWS
- PySpark
- SAP
- Dynamics 365
- Databricks Genie
What this work shows about us.
SAP, Dynamics 365, loyalty, footfall sensors and documents feed one platform, without replacing them.
Dashboards are cut by role, region and category, so a store, a brand and head office each see their own view.
Want to build a similar retail analytics platform? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
What we would add now, moment by moment.
An agent would spot an item about to run out in a store from the forecast, propose a transfer from a nearby store or the warehouse and send it to the planner. The planner approves every move.
An agent would watch delivery times by category and city and tell the operations team where orders are running late, with the cause. Operations decides the fix.
Where this work fits.
- Brands & retailYour brand is meant to help every shopper find what they want and buy it, without wondering.
- Retail analytics & trade promotionsTeams see what made shoppers buy, and which promotion worked and why, before the next one is planned.
- India's leading online beauty retailerShoppers watch live product shows from the beauty retailer on social media and its own site, without lag.
- The Souled StoreThe Souled Store's customers buy in the app or the store, pick up or return anywhere, and get same-day delivery from the nearest shop.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy