South KoreaFood and restaurants2024 – ongoingCJ Foodville
Tous les Jours bakery demand forecasting pilot
CJ Foodville reported sales at least 5% above an earlier average during a bakery forecasting pilot
Problem
Tous les Jours franchisees had to balance unsold bread against shortages. Excess production created disposal costs, while conservative production left customers with fewer choices.
Approach
CJ's AI team and Tous les Jours built demand forecasts from store sales and local trading conditions. They grouped similar stores and used stronger sellers as references for production recommendations. A 6-week pilot tested the recommendations in 5 stores, with headquarters supporting staffing and disposal costs.
Results
Takeaway
The comparison used January–July average sales rather than a control group. Headquarters also supplied operational support, so the reported gain did not isolate the forecasting system's effect.
Categories
- Size
- Large enterprise
- Industry
- Food and restaurants
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
CJ described a forecasting pilot conducted from August 1 to September 13. It reported higher sales and customer counts than the participating stores' January–July averages.
Full details are in the original sources.
