SwedenRetail and e-commerce2019 – ongoingAxfood
In-house demand forecasting and automated store replenishment
Axfood reported 30% fewer promotional forecast errors after replacing an external system
Problem
Stores needed to order enough goods to meet demand without creating excess stock and waste. Promotional sales forecasts contained errors.
Approach
Axfood built its first major in-house AI model on a cloud-based platform in 2019, replacing an external system. The model learned patterns from company data and generated forecasts that drove automatic store orders.
Results
Takeaway
The forecasts fed directly into replenishment decisions, connecting prediction accuracy to stock ordering.
Categories
- Size
- Large enterprise
- Industry
- Retail and e-commerce
- Business function
- Logistics and supply chain
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Axfood described its internally developed forecasting model and its role in automatic store ordering. Its AI strategy head reported an immediate 30% reduction in promotional forecast errors.
Full details are in the original sources.
