Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Econometrics›Croston's Method for Intermittent Demand
Regression model

Croston's Method for Intermittent Demand

Croston's Method for Intermittent Demand Forecasting · Also known as: Croston method, intermittent demand forecasting, Croston Yöntemi — Aralıklı Talep Tahmini

Croston's method, introduced by J. D. Croston in 1972, is a time-series forecasting technique built for intermittent demand series in which periods of zero demand are frequent. Instead of forecasting the raw series, it models the size of demand when it occurs and the interval between demand occurrences as two separate processes.

ScholarGate
  1. Regression model
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Croston's Method
ARIMAOLS RegressionPoisson RegressionTheta Method

When to use it

Use Croston's method when the series is intermittent — many zero observations punctuated by occasional non-zero demand — and you need a per-period forecast for stock control or supply-chain planning. It expects at least about 20 observations and assumes demand size and demand interval follow independent processes, with demand sizes being identically and independently distributed. It is the standard reference method for spare parts and slow-moving inventory, and is less suited to dense series with regular non-zero demand, where ordinary exponential smoothing, Theta, or ARIMA are more appropriate.

Strengths & limitations

Strengths
  • Purpose-built for intermittent series, where it avoids the downward bias that ordinary smoothing suffers from on the many zero periods.
  • Simple and fast: two independent exponential-smoothing recursions with a single smoothing constant.
  • The standard reference method for spare-parts and slow-moving inventory forecasting in stock control and supply-chain planning.
Limitations
  • The classical estimator is biased; the Syntetos-Boylan approximation is often preferred to correct it.
  • Assumes demand size and interval are independent and that demand sizes are IID — assumptions that can fail in practice.
  • Needs a reasonable history (about 20 observations) and gives little guidance for series that are not genuinely intermittent.

Frequently asked

What makes demand 'intermittent'?

Intermittent demand is a series in which many periods record zero demand, interrupted by occasional non-zero observations. Such patterns are common for spare parts and slow-moving inventory, and they break ordinary smoothing methods that assume demand occurs in most periods.

Why split demand into size and interval?

Modelling the size of a demand and the gap between demands separately lets each component be smoothed cleanly without being distorted by the many zero periods. The per-period forecast is then the smoothed size divided by the smoothed interval.

Is Croston's original estimator unbiased?

No. Syntetos and Boylan (2005) showed the classical 1972 estimator is biased and proposed a correction. In practice the Syntetos-Boylan approximation is often used to obtain more accurate intermittent-demand estimates.

When should I not use Croston's method?

When the series is dense with regular non-zero demand it is no longer intermittent, and methods such as ordinary exponential smoothing, the Theta method, or ARIMA will usually forecast better.

Sources

  1. Croston, J. D. (1972). Forecasting and Stock Control for Intermittent Demands. Operational Research Quarterly, 23(3), 289-303. DOI: 10.1057/jors.1972.50 ↗
  2. Syntetos, A. A. & Boylan, J. E. (2005). The Accuracy of Intermittent Demand Estimates. International Journal of Forecasting, 21(2), 303-314. DOI: 10.1016/j.ijforecast.2004.10.001 ↗

How to cite this page

ScholarGate. (2026, June 1). Croston's Method for Intermittent Demand Forecasting. ScholarGate. https://scholargate.app/en/econometrics/croston-method

Related methods

ARIMAOLS RegressionPoisson RegressionTheta Method

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • ARIMAEconometrics↔ compare
  • OLS RegressionEconometrics↔ compare
  • Poisson RegressionEconometrics↔ compare
  • Theta MethodEconometrics↔ compare
Compare side by side →

Similar methods

Exponential SmoothingTheta MethodHolt-WintersETS ModelSARIMAGM(1,1) Grey ForecastingARIMAProphet

Related reference concepts

EM AlgorithmForecasting and Simulation: Models and ApplicationsForecasting and Simulation: Models and ApplicationsForecasting and Simulation: Models and ApplicationsForecasting and Simulation: Models and ApplicationsForecasting and Simulation: Models and Applications

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Croston's Method (Croston's Method for Intermittent Demand Forecasting). Retrieved 2026-07-21 from https://scholargate.app/en/econometrics/croston-method · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
J. D. Croston (1972)
Year
1972
Type
Intermittent demand time-series forecasting
Estimator
Separate simple exponential smoothing of demand size and inter-arrival interval
Outcome
intermittent (count or continuous) demand series
Related methods
ARIMAOLS RegressionPoisson RegressionTheta Method
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account