Out of stock
the direct link between inaccurate sales forecasts and poorly coordinated pricing

Ines Amor

Ph.D. in AI and Data Science

August 20, 2026

A stockout is never an isolated incident: it’s the result of an inaccurate forecast made earlier, and pricing plays a role on three levels, not just one. It can be the cause when a promotion or price reduction is launched without taking available inventory into account. It becomes the consequence when excess inventory is managed through a poorly controlled pricing reflex—such as selling off stock too quickly or, conversely, maintaining a high price based on perceived scarcity. And it remains—all too often overlooked—the quickest lever for curbing demand before the shelf runs empty. A previously published Booper article on forecasting mechanics treats stockouts as input data that needs to be cleaned from the historical record. This article approaches the problem from the other end: stockouts as a quantifiable business consequence of a failed forecast (including pricing) and as the starting point of a vicious cycle that skews sales history, compromises the next forecast, and triggers the next stockout.

Table of Contents

H2 Headings

Booper illustration: shelf with an empty spot, out of stock

Stockouts: A Symptom, Not an Isolated Incident

An empty shelf is immediately noticeable, whether in a store or online. What’s less obvious is what led up to it: an order placed based on a forecast that underestimated actual demand.

A shortage is almost never purely a logistical mishap—a late truck, a supplier that fails to deliver. More often than not, it’s the inevitable consequence of a figure that, just a few weeks earlier, suggested, “We won’t need more than that.”

It is important to distinguish from the outset between stockouts and another problem that appears similar: price markdowns, or “ markdown.” A stockout occurs when inventory is insufficient to meet demand.

A markdown is the opposite—too much unsold inventory—which weighs on the margin. Both are symptoms of an inaccurate forecast, but in opposite ways, and they cannot be addressed using the same strategies, a point discussed further below (§5).

A disruption can also be a pricing decision, not just a forecasting error

There is a third cause, one that is less often cited: stockouts triggered by pricing. An aggressive promotion or price cut launched without being based on reliable forecasts and available inventory can cause demand to surge beyond what inventory can handle—a stockout brought on by a pricing decision, not just by inadequate forecasting upstream.

The problem here is not that the forecast was wrong; it is that the pricing decision did not take it into account.

A previously published Booper article, “Sales Forecasting with AI: Methodology and KPIs,” details the mechanics of calculating a forecast and mentions data breaks as a technical factor that must be isolated before any calculations are made, so as not to skew the historical data used as input. This article delves deeper into this specific point: it explains why this technical precaution exists, the business cost of not taking it, and how an uncorrected data break becomes self-perpetuating.

The Cost of a Stockout, in Order of Magnitude

The retail industry often talks about “inventory distortion,” a term that encompasses two related problems: too little inventory (out-of-stock situations) and too much inventory (excess inventory, markdowns). Both are costly.

But one carries significantly more weight than the other, and it's not always the one you'd expect.

$1,200 billion

This is the global cost of stockouts in 2026, out of a total of $1,700 billion in inventory distortion (stockouts + overstock) worldwide. Empty shelves alone account for $690.9 billion in losses (IHL Group, 2026 Inventory Distortion Study).

Two key figures to note in this study: the cost of stockouts ($1,200 billion) is more than double that of overstocking ($572 billion). In retail, the instinct is often to focus on overstocking—unsold merchandise is visible; it sits on the shelves; it eventually goes on sale.

A missed sale, on the other hand, leaves almost no direct trace in the books: a sale that never took place generates neither an invoice nor a visible loss entry. Yet, on a global scale, it is the more costly of the two problems, precisely because it is the most difficult to measure without rigorous forecasting.

The vicious cycle: A breakup skews the sale it prevents

This is the core concept of this article, and it is rarely explained clearly: a data break doesn't just cost you a sale in the moment. It permanently skews the data that will be used to calculate the next forecast.

Here's how bias develops, step by step:

A product is out of stock for several days during a week of high demand, a seasonal peak, a sales promotion, or due to weather conditions.
The system records this week's actual sales: they are low, by default, since the product was simply no longer available for purchase.
Nothing in this raw data distinguishes between “demand has fallen” and “demand existed but could not be realized.”
A forecasting model (statistical or AI) that learns from this historical data without correcting it interprets this dip as a sign of weak demand and forecasts lower demand for the corresponding period in the future.
Fewer forecasts mean fewer orders. Fewer orders mean another likely stockout of the same product during the same period.

The loop feeds back on itself. Each iteration reinforces the previous error.

Demand censoring. That is the name statisticians give to this bias: the observed data do not reflect true demand; they reflect demand filtered by available inventory.

Without explicit correction, a forecasting system—no matter how sophisticated—optimizes based on a biased signal and produces a consistent, reproducible bias that worsens over time when applied to the same benchmarks.

A side effect: cannibalization

The situation becomes even more complicated due to cannibalization: when a product is out of stock, some of the demand for it shifts to a substitute product, causing sales of that substitute to rise artificially while sales of the out-of-stock product plummet. If left unaddressed, the forecast for the substitute product will also be skewed (upward this time) for the following period.

The Cost to Customer Loyalty, Beyond the Lost Sale

The lost sale at the moment of stockout is the visible part of the cost. The less visible—but equally real—part is what goes through the customer’s mind when they find the shelf empty.

31%

Customers who encounter an empty shelf buy the product elsewhere on the spot—an immediate switch to a competitor, not simply postponing the purchase (Gruen, Corsten & Bharadwaj, a GMA/ECR study of more than 71,000 consumers in 29 countries, reported by Harvard Business Review, May 2004).

The same study estimates that the average share of revenue lost by a retailer due to out-of-stock situations is approximately 4 percent—a figure consistent with the proportion of global out-of-stock situations cited in §2. But the most useful figure is not that one: it is 31 percent.

A missed sale costs more than just a lost sales opportunity. In nearly one-third of cases, it costs the store a customer who has just discovered (on the spot) that a competitor had something that this store or website did not.

The real cost isn't today's sale. It's the customer who, once they've gone to a competitor, doesn't automatically come back—even when the shelves are full the following week.

When this experience is repeated with the same products and the same customers, it cannot be remedied by a promotion the following week: it builds up over time and erodes the likelihood that a customer will return to the same store to buy that product the next time.

That is why stockouts are not just a supply chain issue. They are a forecasting issue (because forecasting determines in advance whether inventory will be sufficient) and a customer retention issue, because it is customer loyalty—not just immediate revenue—that is at stake every time a shelf is empty.

Ultimately, it comes down to pricing. The speed at which a price readjusts once inventory is back in stock—neither set too high due to a scarcity bias nor sold off at a discount out of panic—directly affects the likelihood of winning back a customer who has already gone elsewhere.

Stockouts and markdowns: two opposing symptoms of the same poor forecast

Stockouts and markdowns share the same root cause (a forecast that did not match actual demand), but they manifest in opposite ways, and confusing the two leads to applying the wrong solution to the wrong problem.

Criterion	Out of stock	Markdowns / Excess Inventory
Source: Forecast	Underestimated demand: The order covers less than what could have been sold	Overestimated demand: The order exceeds sales
Visible symptom	Shelf is empty; product is unavailable online	Excess inventory, sales of markdown
Immediate consequence	A lost, irreversible sale—it never took place	Margins are squeezed, but the inventory is still saleable
Effect on the history	Adjust the demand downward (see §3) for the period in question	May artificially inflate demand if sales are driven by forced promotions
Booper Lever	GENIUS Predict + GENIUS Monitoring for forecasting and early detection; GENIUS Price to defuse the situation through pricing before it escalates	Dedicated support for special offers & markdown

For the opposite problem to the one discussed here (excess inventory that’s eating into margins), Booper offers specialized support: markdowns But that’s not the focus of this article: a stockout is never resolved by selling a product that, by definition, is no longer in stock.

Both warrant a separate diagnosis, even though the root cause (a poorly calibrated forecast) is often the same.

The wrong reflex: a break that escalates into a poorly controlled move

The confusion between the two sometimes takes a more insidious form: a poor transition from one to the other. A stockout creates pressure to react quickly as soon as the restock arrives—to urgently order a make-up shipment, then sell it at a deep discount once demand has dropped—or, conversely, to maintain a high price out of a scarcity mindset.

In both cases, this isn't a new mistake: it's the same underlying governance issue (a pricing process that makes decisions without consulting the forecast) replaying itself in a different form.

Breaking the Vicious Cycle in Four Steps

The vicious cycle described in §3 is not a statistical inevitability. It can be broken through a methodical analysis of historical data and by detecting the break itself more quickly.

Identify periods of disruption in the historical data

Explicitly mark, product by product, the days or weeks when inventory was zero or close to zero, rather than letting those points blend into the series as normal sales.

Correct the request, not just delete it

Simply excluding periods of stockouts also skews the calculation. Best practice is to estimate what demand would have been by comparing it to similar products, seasonality, or the trend observed immediately before the stockout.

Increase the order quantities for items that are chronically out of stock

A product that consistently sells out every cycle has, by definition, actual demand that exceeds its recorded demand. The forecast should take this fact into account rather than simply replicating an already biased historical record.

Wrap up with real-time monitoring

Detecting a disruption as soon as it begins (rather than in a monthly report) limits its duration. A shorter disruption means less bias introduced into the historical data, and therefore a less distorted subsequent forecast.

What Changes When a Forecast Explains Its Deviations

Correcting historical data after the fact is necessary, but insufficient if the next forecast remains a black box. What really changes the equation is a forecast capable of explaining why it predicts a particular figure, and a monitoring system capable of flagging a disruption as it’s happening—not after it’s been going on for three weeks.

Price as a Tool for Managing Demand

This isn’t the only option. For a product with tight inventory or low forecast confidence, price is also a tool for managing demand: adjusting the price or scaling back a promotion helps keep demand within the limits of available inventory—a form of demand shaping through price that complements pure supply-chain arbitrage.

A pricing team that coordinates with the forecasting team can mitigate the risk of a stockout before it occurs.

+5 to 10%

This is the margin gain that McKinsey observes among retailers who use dynamic pricing—based on demand and inventory levels—rather than a fixed price (McKinsey & Company, “Dynamic Pricing in e-Commerce”). It is precisely this margin that is squandered by a poorly managed stockout: a rush order to restock, followed by a markdown or, out of habit, maintaining a high price—all because pricing isn’t aligned with inventory levels.

At Booper

GENIUS Predict and GENIUS Monitoring: Early Detection, Accurate Correction

The GENIUS Predict module projects demand over several rolling weeks based on three scenarios— Conservative, Balanced, and Aggressive—with an “AI Explanation” section that lists the factors influencing the forecast. A category manager can thus determine that a low forecast is due to a period of stockout that was not properly corrected in the historical data, rather than taking it at face value. At the same time, GENIUS Monitoring acts as a real-time alert center for stockouts, price anomalies, and competitor price discrepancies, helping to limit the duration of a stockout before it permanently skews the sales history.

The break is reversible

The vicious cycle described in this article is not inevitable, provided it is treated for what it is: a forecasting problem, not just a logistics or restocking problem.

-65%

AI-driven forecasting reduces forecasting error by 20 to 50 percent compared to traditional methods and can cut out-of-stock situations and the resulting product unavailability by up to 65 percent (McKinsey, “AI-driven operations forecasting in data-light environments,” February 2022).

This potential does not materialize on its own. It requires an organization that actively corrects the bias introduced by its past disruptions, rather than allowing its model to learn indefinitely from historical data that it already knows to be skewed.

This is as much a matter of governance as it is of statistical models; the reference guide for this topic explains what turns a forecast into an actionable decision, rather than just a number that’s looked at but not acted upon. And for the complete calculation process (methodology, KPIs, error formulas) , the Booper article “Sales Forecasting with AI: Methodology and KPIs” remains the go-to technical resource.

A Checklist to Follow Before Relying on Your Forecast Despite Stockouts

Do you know what portion of your sales history is actually demand masked by a stockout?
Are your chronic disruptions identified product by product, or are they buried in an overall average?
Does your forecast include an adjustment when inventory reaches zero, or does it treat "0 sales" as "0 demand"?
Do you know how many customers you lose (not just how many sales) with every recurring stockout?
Does your monitoring system detect an outage on the same day, or only in a month-end report?
Is your pricing strategy (promotions, price cuts, restocking) based on inventory levels and the reliability of your forecast, or is it decided independently of those factors?

Want to know where your data breaks are skewing your forecast?

Spend 30 minutes with our team to identify products that are chronically out of stock and determine how much they’re actually costing you in terms of both your sales forecasts and customer retention.

Let's plan an exchange →

Frequently Asked Questions

Why is a stockout linked to poor sales forecasting?

A stockout usually occurs because the forecast that triggered the order underestimated actual demand: the ordered inventory is insufficient to meet the demand as it arises, the shelf empties, and the lost sales become an immediate loss.

It’s almost never a purely logistical mishap—a delayed truck, a supplier that falls short. More often than not, it’s the inevitable consequence of a figure that, a few weeks earlier, indicated that no more than that would be needed.

There is a third, less commonly cited cause: a disruption triggered by a pricing decision—an aggressive promotion launched without being based on available inventory and the reliability of the forecast can cause demand to surge beyond what inventory can handle.

In all three cases, the problem isn't just logistical: it's a matter of forecasting—and, in the third case, of coordination between pricing and forecasting. We discuss this coordination in detail in our article on sales forecasting, methods, AI, and best practices.

How does a stockout distort sales history?

During a stockout, recorded sales drop to zero or near zero—not because demand has disappeared, but because it could not be met due to a lack of inventory. A forecasting model that detects this decline without correcting for it interprets a lack of supply as a lack of demand.

Statisticians have a name for this bias: demand censoring. The observed data do not reflect true demand; rather, they reflect demand filtered by the available inventory at the time of sale. We discuss this need for depth in our article on the sales history required for accurate forecasting.

This is how the vicious cycle closes: fewer forecasts mean fewer orders; fewer orders mean another likely shortage of the same product during the same period, with each iteration reinforcing the previous error.

A side effect makes the situation worse: cannibalization. When a product is out of stock, some of the demand for it shifts to a substitute, causing its sales to rise artificially, which in turn skews the forecast for the substitute product—this time upward.

What is the difference between an out-of-stock item and a price markdown?

A stockout occurs when inventory is insufficient to meet demand—an empty shelf, a lost sale that can never be recovered because it never happened. A markdown (or “ markdown ”) is the opposite: too much unsold inventory, which eats into profit margins and must be cleared out, often through promotions.

Both stem from the same source (an inaccurate forecast) but in opposite directions, and they cannot be corrected using the same strategies: correcting a stockout requires improving the reliability of forecasting and restocking, while correcting a markdown requires managing the sales rate and the depth of the discount. We discuss this second lever in detail in our article on markdown and “ markdown ” without sacrificing profit margins.

A common mistake is to let one situation spiral into the other: a stockout creates pressure to react quickly as soon as new inventory arrives, which leads to rushing to order a replenishment, and then selling it at a deep discount once demand has dropped.

In this case, it is not a new mistake but the same initial governance issue (a pricing process that makes decisions without consulting the forecast) replaying itself in a different form.

How much does a stockout cost a retailer?

According to IHL Group (2026), stockouts cost approximately $1,200 billion annually worldwide, of which $690.9 billion is attributable to empty shelves alone—more than the cost of overstocking ($572 billion) over the same period. Booper offers dedicated support: see our page on AI-powered sales forecasting.

However, this direct cost is not the most telling indicator. According to a study by Gruen, Corsten, and Bharadwaj (GMA/ECR, as reported by the Harvard Business Review), 31% of customers who encounter an empty shelf purchase the product elsewhere on the spot—an immediate switch to a competitor, not simply a delay in the purchase.

The same study estimates that the average share of revenue lost by a retailer due to stockouts is approximately 4 percent—a figure consistent with the global percentage cited above—but the true cost isn’t the sale lost that day: it’s the customer who, once they’ve gone to a competitor, doesn’t automatically return even when the shelf is fully stocked the following week.

When this experience is repeated with the same products, it builds up over time and erodes the likelihood that a customer will return to the same retailer to purchase that product, making stockouts as much a customer loyalty issue as a supply chain issue.

How can we break the vicious cycle of a breakup, followed by a wrong prediction, followed by another breakup?

In four steps, described in this article. First, explicitly identify periods of disruption in the historical data, product by product, rather than letting them blend into the series as normal sales.

Next, adjust the demand rather than simply excluding it: estimate what it would have been based on comparisons with similar products, seasonality, or the trend observed just before the disruption; simply excluding these periods also skews the calculation.

Step 3: Revise upward the forecast for items that are chronically out of stock, since a product that runs out of stock every cycle has, by definition, actual demand that exceeds its recorded demand.

Finally, round out the process with real-time monitoring: detecting a disruption as soon as it begins—rather than in a monthly report—limits its duration and, therefore, the bias it introduces into the historical data for the next forecast. We detail this comprehensive method in our article on AI-powered sales forecasting, methodology, and KPIs.

Can artificial intelligence reduce stockouts?

Yes, to a significant extent. According to McKinsey, AI-driven forecasting reduces forecasting error by 20 to 50 percent compared to traditional methods and can cut out-of-stock situations and the resulting product unavailability by up to 65 percent.

This potential does not materialize on its own: it requires an organization that actively corrects the bias introduced by its past data gaps, rather than allowing its model to learn indefinitely from historical data that it already knows to be distorted; this is as much a matter of governance as it is of statistical modeling.

Pricing serves as a complementary tool to this forecasting process: when operating with tight inventory levels, adjusting the price or reducing the scope of a promotion helps keep demand within the limits of available inventory—a form of demand management through pricing that complements supply chain optimization. We discuss this approach in detail in our article on dynamic pricing with omnichannel consistency.

According to McKinsey, retailers who use dynamic pricing based on demand and inventory levels—rather than fixed prices—see a 5 to 10 percent increase in margins—precisely the margin lost due to a poorly managed stockout, between rushing to place a replacement order and marking down the item or keeping the price high out of habit.

Out of stock
the direct link between inaccurate sales forecasts and poorly coordinated pricing

Stockouts: A Symptom, Not an Isolated Incident

A disruption can also be a pricing decision, not just a forecasting error

The Cost of a Stockout, in Order of Magnitude