Allocating stock across sites that compete for it
retail supply-chain operator · Gulf
The shape of this problem
The same judgment, made differently every time
This is one of our own builds, not a client engagement. It is capability evidence and it is described as such.
The problem
Supply-chain teams needed to place limited inventory across locations while balancing expected demand, service levels, holding cost, and transfer constraints. Those constraints are only solvable together. Correcting one at a time - closing a service gap here, then a transfer cost there - produces a sequence of locally reasonable moves that add up to a worse plan, and planners were doing exactly that across thousands of product-location decisions every cycle.
What we built
We built a pipeline that estimated demand by product and location, calculated allocation priorities, applied stock and logistics constraints, and generated recommended transfers and replenishment quantities alongside scenario dashboards.
What moved
| Measure | Before | After |
|---|---|---|
| Inventory-allocation cost | † | down 20% |
| Product availability | † | up 15% |
| Manual allocation planning time | † | down 55% |
† Measured against the prior level of the same measure. The source publishes the size of the movement, not the figure it moved from.
Inventory-allocation cost
Measured against the client's own prior process, indexed to 100. The source publishes the size of the movement, not the absolute figure it moved from.
Product availability
Measured against the client's own prior process, indexed to 100. The source publishes the size of the movement, not the absolute figure it moved from.
Manual allocation planning time
Measured against the client's own prior process, indexed to 100. The source publishes the size of the movement, not the absolute figure it moved from.
Figures are drawn from the practice's own delivery records for the engagement named, measured against the process that preceded it. They have not been through third-party audit, and none is presented as an average across clients.
What it turned on
Infeasibility reporting and logged overrides kept it operationally credible - the system stated plainly when the requested service levels could not all be met, and let local knowledge modify a recommendation without concealing the tradeoff being made.
- Service line
- Forecasting & Planning AI
The finding matters more than the number here. Both cases repaired data definitions before modelling, which is the practice's whole thesis in miniature.
Start here
Which of the four is yours?
Tell us the documents and the monthly volume and we will send the two closest records, with the proof behind each and the honest note where the match is partial.
You get a reply within one working day, from the engineer who would do the work - not a sales sequence.