Evaluating new store locations with AI
Use Case: Use AI to lower costs and improve accuracy of sales predictions for new stores
FamilyMart is a convenience store chain with approximately 24,000 locations around the world. When deciding on possible new store locations, they tried predicting average daily sales for one year. To do this, they ran multiple regression analysis based on factors like population, number of parking spots, and the like. However, their predictions varied wildly in accuracy.
FamilyMart started looking for AI solutions to help them get more accurate predictions. They contacted seven companies about building a proof of concept model, but most came back with quotes with high initial costs. Since it was an experimental proof of concept, they decided to go with the MAGELLAN BLOCKS Model Generator (regression type), which you can use starting at just $1,000 per month.
With their new BLOCKS model, the difference between predicted and actual sales was within about $500 for approximately 80% of stores. It was also much faster to implement. With BLOCKS, they just needed to provide the data to train the model, so they could start making predictions about 4–5 times faster than their old system. And in terms of cost, BLOCKS cost them less than half of what they were paying before. FamilyMart is now making plans to use AI with BLOCKS to evaluate locations for new stores.
Companies are seeing success with BLOCKS.
See More Customer Stories