How I Think About Supply Chain
After 15 years of optimizing supply chains across automotive and semiconductor industries, I've developed a clear philosophy about what works.
Before optimizing anything, build a model that captures the system's real behavior — variability, constraints, and feedback loops. Spreadsheets show averages. Simulation shows reality.
Every project should have a clear, quantifiable outcome. Not 'improved efficiency' but '$2.4M saved' or '20% cycle time reduction.' If you can't measure it, you can't manage it.
The best analysis in the world is useless if it sits in a PowerPoint. Build systems that translate insight into automated action — with appropriate human guardrails.
Supply Chain Simulation
End-to-end discrete-event simulation models that capture stochastic behavior, multi-echelon inventory dynamics, and capacity constraints. Used for scenario planning, disruption response, and strategic network decisions.
Network & Cost Optimization
Mathematical optimization models for logistics network design, facility location, routing, and duty/tariff analysis. Finding provably optimal solutions to complex multi-variable cost problems.
ML-Driven Forecasting
Machine learning models for intermittent and lumpy demand patterns — the type of demand traditional methods handle poorly. Combining installed base data with statistical and ML approaches.
AI-Powered Process Automation
Exploring agentic AI for supply chain workflows — autonomous agents that handle routing decisions, demand signal processing, and report generation with human-in-the-loop oversight.