Leak 23 · Inventory & Working Capital - Stockouts on high-value SKUs

The fast, high-margin item is out again. The customer buys elsewhere, and the sale is never recorded because it never happened.

Diagnostic note. Symptoms, required records, an initial check, and possible fixes. This shorter note does not include a full worked example.

What is it?

Stockouts on the wrong items cost revenue directly, cost margin when the order is filled by an expensive rush, and cost relationships when customers learn they cannot rely on you. They are the mirror image of excess stock: the money is tied up in items that do not move while the items that do move run out.

Family
Inventory & Working Capital
Primary owner
Inventory Manager
Secondary owners
Sales Managers, Purchasing Manager
Primary impact
Revenue / margin
Typical data source
ERP stock levels, backorders, lost-sale records if any
Detection difficulty
30-day measurability

Ask yourself

Do you track lost sales, and can you name the ten items that stocked out most often last year?

Yes, partially, no, or don’t know. “Don’t know” is the most useful answer, because it points at the test below.

What does it look like?

Warning signs. None of these proves the leak exists. They tell you where to look.

  • Repeated backorders on A-class items.
  • Emergency purchases at premium cost to fill routine orders.
  • Fill rate not measured, or measured only in aggregate.
  • Salespeople keeping their own stash of critical items.

What data do I need?

The minimum viable set. Most of it is already in your ERP.

Field
Item stock levels and backorder history
Item class and gross margin
Lost sale or substitution records
Expedite purchases linked to stockouts

The initial check

Start with a small sample. Gathering the exports, agreements, or observations is separate from running the check; agree that work with the person who owns the records.

  1. 1Export backorder lines for the last quarter with item and gross margin.
  2. 2Rank items by backorder frequency and count the A-class items in the top twenty.
  3. 3For those, check current reorder point against average demand during lead time.
Stockout cost per item = (lost sales × gross margin) + expedite premiums + backorder handling time

Then ask one question: Are the items that run out the ones with the lowest safety stock relative to their demand variability?

How much could it be costing us?

A conservative range, not a headline. The goal is a number management can trust enough to investigate.

Estimated lost gross profit on stockout events + expedite costs, for A-class items, × share preventable by parameter changes

Common root causes

Fixes fall into three layers. Not every problem needs software, and almost none needs AI first.

Process
Replenishment parameters are not reviewed by item class, so A items get the same treatment as C items.
Data
Lost sales are not recorded, so the cost of stockouts is invisible.
Technology
No exception report for items approaching stockout before it happens.

What should we do?

Start with the simplest intervention that could solve it. Move down the list only if the one above is not enough.

  1. Level 1

    Visibility

    A weekly fill-rate and stockout report by item class.

  2. Level 2

    Parameters

    Higher service targets and reviewed safety stock for A items, funded by cuts on C items.

  3. Level 3

    Workflow

    A projected-stockout alert that gives purchasing time to act before the item runs out. See the backorder workbench example project.

Where AI helps

  • Recording lost sales from quote and order conversations where the item was unavailable.
  • Demand forecasting on items with lumpy or customer-driven demand.

Where AI probably doesn’t

Most stockouts trace to a reorder point that is too low. Fix the parameters first.

Before you call it a leak

  • Raising stock on A items has a cost. Compare it to the lost margin before adding inventory everywhere.

Think this might be happening in your business?

Turn the finding into a next step.

If the numbers say there is something there, send us what you found and we will help you decide whether it is worth a full investigation. No transaction files needed for that conversation.

Let’s start with one thing.

What would better performance look like?

Bring a result you want to improve, a symptom, or a workflow you already understand. You do not need to know the bottleneck yet. We’ll help choose what to investigate first.

No transaction files needed for the first conversation.