Stockout

As explained in Demand Forecasting Best Practices

An out-of-stock period is a time interval during which a product is unavailable because no usable inventory can be supplied to customers.

A stockout is a period when customers cannot obtain a product because no usable inventory can be supplied. During that interval, observed sales no longer represent underlying demand: sales may fall to zero even while customers still want the product. section 3.2 section 3.0

Treat stockouts as demand-data problems as well as service problems:

• Track inventory and sales together to identify periods when demand is unconstrained and periods when sales are censored by availability. section 3.2
• Exclude or censor stockout periods when training forecasts so unusually low sales do not produce an artificially low demand forecast. section 3.2
• Check apparent inventory carefully: inaccurate counts, unshelved units, or unacceptable freshness can create effective shortages despite recorded stock. section 3.2
• Account for substitution because customers may switch products, raising sales for substitutes while reducing sales for the unavailable item. section 3.3

Chocolate and vanilla ice cream

If chocolate ice cream is unavailable, some customers choose vanilla. Vanilla sales then exceed its original demand while chocolate sales fall below its demand. Forecasting sales without recognizing the stockout overstates vanilla and understates chocolate; a family-level ice-cream forecast can reduce, but not eliminate, this distortion. section 3.3

Figure 3.1 Sales vs. inventory for a product sold online

Use the sales-versus-inventory figure to inspect how product availability changes observed sales over time. section 3.2

How Demand Forecasting Best Practices covers it

How deep it goes

Defines stockouts, explains censoring and hidden shortages, and discusses substitution without specifying forecasting implementation details.

Examples

Uses online sales and inventory traces, ice-cream substitution, and retail shelf or freshness shortages as concrete cases.

What it assumes

Assumes familiarity with sales and inventory data while teaching the distinction between observed sales and customer demand.

What you can do after

Diagnose demand distortion by identifying stockout periods, censoring affected observations, and recognizing substitution effects.

How it connects

Connects stockouts to demand, sales, inventory, forecasting, lost sales, substitution, cannibalization, and customer collaboration.

liveBookmanning.com

Read Demand Forecasting Best Practices on liveBook Get the book at manning.com

Related concepts

• language modelused by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• substitutionproduces · Substitution is the replacement of one item, value, expression, option, or role with another serving an equivalent or comparable purpose.
• shortage-censoringused by · Shortage-censoring is the exclusion or adjustment of observations from periods when recorded sales are limited by product shortages.
• lost saleproduces · A lost sale is a potential purchase that does not occur because the requested product or service cannot be provided when needed.

This explainer was generated by Manning's knowledge graph from the text of Demand Forecasting Best Practices. The section links point to the parts of the book it draws on.