Schneider Electric saves €8 million in transportation costs by optimising global supply chain with machine learning

Schneider Electric operates a complex supply chain spanning 240 manufacturing facilities and 110 distribution centers worldwide. Coordinating raw material acquisition and product delivery across this footprint involves hundreds of thousands of transportation policies and flow constraints.

Schneider Electric developed a machine learning model to analyse its entire global transportation network, ingesting 200,000 transportation policy data points and 130,000 flow and routing constraints. To simplify the model, 300,000 individual SKUs were consolidated into 1,800 product groups based on attributes including origin, stocking type, and product family, a 99.4% reduction. The input data also included more than 150 initial scenarios. The ML model assessed existing lanes, freight rates, and policy rules, identifying optimal product flow paths for both inbound raw material sourcing and outbound distribution.

The optimisation programme delivered €8 million in transportation cost savings, the primary financial outcome of rationalising routing decisions across a 350-facility global network. Alongside cost reduction, the initiative achieved measurable improvement in container utilisation across international freight lanes, reducing wasted capacity that compounds costs at scale. The SKU consolidation also simplified ongoing supply chain planning, establishing a leaner product taxonomy for future modelling. Key metrics:

• €8 million in transportation cost savings
• 300,000 → 1,800 product groups (99.4% SKU reduction)
• 200,000+ transportation policy data points modelled
• 130,000 flow and routing constraints incorporated
• 150+ scenarios evaluated to identify optimal product flows

• Simplify the problem before modelling. Consolidating 300,000 SKUs into 1,800 product groups simplified the model.
• Mature supply chains still contain hidden cost. ML can surface savings in a large, established network by systematically exploring the full constraint space.
• Model policies and physical constraints together. Treating transportation policy rules and flow constraints as a unified problem lets a single model account for both.