United StatesFood and restaurants2025 – ongoingMondelez International
Machine-learning demand forecasting for supply-chain planning
Databricks reported 2–3% lower inventory waste with Mondelez demand forecasting
Problem
Excess production created unsold inventory.
Approach
Mondelez used SKU forecasting models for supply planning. Forecasts supported short- and long-term decisions.
Results
2–3%inventory waste reduction, per Databricks
Takeaway
Forecasts supported planning from 6 weeks to 2 years ahead. The reported waste reduction covered finished goods and plant inventory.
Categories
- Size
- Large enterprise
- Industry
- Food and restaurants
- Business function
- Logistics and supply chain
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
[1]Databricks2025
Databricks described SKU demand forecasts used for short- and long-term supply planning. It reported a 2–3% reduction in finished goods and plant inventory waste.
Full details are in the original sources.
Added 1 Nov 2026 · Updated 1 Nov 2026