JUST-IN-TIME
Definition
Just-in-time (JIT) is an industrial and logistical system that involves producing and delivering goods only when they are needed, in the exact quantities required
Developed at Toyota in the 1950s, this principle aims to minimize intermediate inventory, work-in-progress, and waste
For retail pricing, just-in-time has direct consequences: less excess inventory to mark down, but a greater reliance on the accuracy of demand forecasting.
More frequent deliveries, fewer markdowns
Fresh Products — Yogurt and Prepared Meals
annual savings in this category, thanks to the switch to just-in-time delivery with suppliers.
Health-related write-off rate prior to the transition to just-in-time
Markdown rate after biweekly deliveries adjusted to meet demand
Why it matters
- Significantly reduce costs —including storage and inventory financing costs —which frees up cash flow and improves profitability.
- Minimize markdowns —which result from excess inventory—by putting only the quantities corresponding to projected demand into circulation.
- Improve the freshness of the product selection (by stocking shelves with recent products rather than older inventory), which enhances the perception of quality.
Real-world example
A fresh-food retailer is shifting part of its supply chain (yogurts, prepared meals) to a just-in-time model with its main suppliers
Before the switch, each store received weekly deliveries in large quantities, with a food waste rate (expired products) of 3.8%
After the switch, deliveries shifted to a biweekly schedule adjusted to the demand forecast by AI models. The write-off rate dropped to 1.9%, representing an annual savings of €1.2 million for the category in question.
How to measure and use it
Implementing just-in-time in retail requires three conditions: reliable demand forecasting at the point of sale (AI models are essential to achieve the necessary level of detail), responsive upstream logistics (suppliers capable of delivering on short cycles with high service levels), and precise management of contingencies (stockouts, unexpected demand spikes)
Pricing can be used to smooth out demand when inventory is tight (a slight price increase to slow sales, a slight decrease to speed them up).
Common pitfalls
- Switching to JIT without validation: supplier reliability—a supplier-side shortage immediately becomes a customer-side shortage.
- Applying JIT to unsuitable products: slow-moving items or those with long lead times are not eligible.
- Ignoring operational risk: a strike, a health crisis, or a logistics disruption immediately becomes apparent to customers.
We explore this topic in more depth in our article on calculating price elasticity using data.
FAQ
Just-in-time (JIT) is an industrial and logistics management system that involves producing and delivering goods only when they are needed, in the exact quantities required. Developed at Toyota in the 1950s, this principle aims to minimize intermediate inventory, work-in-progress, and waste.
No
It works well for fast-moving products with short lead times (fresh produce, certain standard manufactured goods)
It is risky for seasonal products with long lead times (seasonal apparel, Christmas toys).
An upstream inventory transfer
Suppliers must maintain their own inventory to deliver on a just-in-time basis, which can erode their profitability if the terms of the arrangement are not negotiated (volume commitment, forecast sharing).
Yes, and it's becoming more and more common. Dropshipping and pre-order models are extreme forms of JIT, where the distributor doesn't even stock the product until a customer places an order.
The method consists of calculating price elasticity using data by cross-referencing sales history and price variations observed over a stable period, free of interfering promotional effects.
This approach is based on AI-powered retail sales forecasting that takes into account seasonality, events, and external signals to anticipate actual demand rather than simply reacting to it.
You might also be interested in these articles
AI transforms sales forecasting by precisely separating baseline demand from promotional uplift. This granular SKU-by-store analysis enables real-time inventory adjustments and margin optimization. A key finding: the use of predictive solutions can reduce spoilage of perishable goods by up to 15%.
A budget that is recalculated with every new forecast loses its functionas a commitment. A forecast that is forced to match the budget loses its predictive value. Both of these pitfalls stem from the same tendency: treating an annual financial commitment and a continuous statistical estimate as a single figure. This guide explains why this confusion is costly—in both directions—and how to clearly separate the two exercises without pitting them against each other.
A sales forecast has almost never failed because the statistical model was flawed. It fails later, when no one knows who is supposed to validate it,adjust it, or defend it against a budget that says otherwise.
This guide does not go into detail about the mechanics of calculating a forecast—a dedicated article by Booper already covers that topic in depth (link below). It asks the question that determines whether all these mechanics serve any purpose: how does a sales forecast become a basis for action, rather than just another number we look at without taking any action?