Services
Seven practice areas, built on one modeling discipline.
Each area stands alone, and most engagements combine two or three. They share a data layer, a standard of proof, and the same commitment to handing you a model you can run yourself.
- 8 to 14 weeks
Supply Chain Network Design
Where things should be made, stored, and shipped from.
Network design answers the questions that are expensive to get wrong and awkward to revisit: how many distribution centers you need, where they belong, which plants serve which markets, and what a facility move actually costs once freight, labor, inventory, and service are counted together.
- Mixed-integer programming
- Capacitated facility location
- Cost to serve modeling
- 6 to 12 weeks
Supply Chain Simulation and Digital Twins
Test the change before it touches the floor.
Optimization tells you what the best plan looks like when the world behaves. Simulation tells you what happens when it does not: when the truck is late, the line goes down, the picker calls out, and demand arrives in a lump rather than a curve.
- Discrete event simulation
- Agent based modeling
- Queueing theory
- 6 to 10 weeks
Demand Forecasting and Planning
Forecasts that planners trust enough to act on.
Forecast accuracy is a means, not an end. The question that matters is whether the forecast changes a decision: how much to buy, how much to build, how much capacity to hold. We build forecasting systems around those decisions and measure them by the cost of the errors they produce, not by accuracy percentage alone.
- Hierarchical time series
- Gradient boosting
- State space and exponential smoothing
- 6 to 10 weeks
Inventory Optimization
Less working capital, better service, on purpose.
Most inventory imbalance is not a volume problem, it is a placement and policy problem. The same total dollars, positioned differently and governed by parameters that reflect real lead time and demand variability, routinely deliver higher service.
- Multi-echelon optimization
- Guaranteed service models
- Demand and lead time distribution fitting
- 5 to 10 weeks
Transportation and Route Optimization
Fewer miles, fuller trailers, tighter windows.
Freight is the line item most exposed to small structural improvements. Better consolidation, smarter mode selection, tighter routing, and a bid built on realistic lane volumes each move the number, and they compound.
- Vehicle routing problems
- Column generation
- Metaheuristic search
- 10 to 16 weeks
S&OP and Integrated Business Planning
One plan the whole business is actually holding.
Many sales and operations planning processes produce a meeting rather than a decision. The demand number and the financial number do not reconcile, supply constraints arrive too late to matter, and the escalations that need an executive never reach one.
- Process design
- Constraint based planning
- Scenario modeling
- 4 to 12 weeks
Supply Chain Analytics and Data Engineering
The plumbing that keeps the models honest.
Every analysis on this site depends on data that is complete, current, and defined the same way twice. That is usually the hardest part of the engagement and the part that determines whether the work survives past the final presentation.
- Python and SQL
- Transformation and orchestration frameworks
- Cloud data warehouses
Combinations
The areas that work best together.
Sequencing matters more than scope. These pairings come up often enough that we plan for them rather than treating them as separate projects.
Network design plus simulation
Optimization proposes the footprint; simulation stress tests it against demand variability and disruption before capital is committed.
Forecasting plus inventory
Probabilistic forecasts feed safety stock directly, so the two models stop disagreeing about the same uncertainty.
S&OP plus analytics engineering
A redesigned cycle only holds if the numbers arrive on time. The data layer is usually the difference between a process that sticks and one that lapses.
Not sure where you fit
Most people arrive with a decision, not a service category.
Describe the decision and the constraint you are stuck on. We will tell you which of these it actually is, and how long it would take.