Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing

Steven Prestwich; S Armagan Tarim; Roberto Rossi; Brahim Hnich

doi:10.1016/j.ijforecast.2014.01.006

Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing

Steven Prestwich, S Armagan Tarim, Roberto Rossi, Brahim Hnich

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

Croston’s method is generally viewed as being superior to exponential smoothing when the demand is intermittent, but it has the drawbacks of bias and an inability to deal with obsolescence, where the demand for an item ceases altogether. Several variants have been reported, some of which are unbiased on certain types of demand, but only one recent variant addresses the problem of obsolescence. We describe a new hybrid of Croston’s method and Bayesian inference called Hyperbolic-Exponential Smoothing, which is unbiased on non-intermittent and stochastic intermittent demand, decays hyperbolically when obsolescence occurs, and performs well in experiments.

Original language	English
Pages (from-to)	928-933
Journal	International Journal of Forecasting
Volume	30
Issue number	4
DOIs	https://doi.org/10.1016/j.ijforecast.2014.01.006
Publication status	Published - Oct 2014

Keywords / Materials (for Non-textual outputs)

Intermittent demand
Croston’s method
Bayesian inference

Access to Document

10.1016/j.ijforecast.2014.01.006

1307.6102v1
© Prestwich, S., Tarim, S. A., Rossi, R., & Hnich, B. (2014). Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing. International Journal of Forecasting. 10.1016/j.ijforecast.2014.01.006
Submitted manuscript, 197 KB

http://arxiv-web3.library.cornell.edu/abs/1307.6102

Confidence-based optimization for inventory management at a local grocery store
Rossi, R. & Yao, X.
1/09/13 → 31/08/14
Project: University Awarded Project Funding

Cite this

@article{d177019d92ac46f69a00948d47437738,

title = "Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing",

abstract = "Croston{\textquoteright}s method is generally viewed as being superior to exponential smoothing when the demand is intermittent, but it has the drawbacks of bias and an inability to deal with obsolescence, where the demand for an item ceases altogether. Several variants have been reported, some of which are unbiased on certain types of demand, but only one recent variant addresses the problem of obsolescence. We describe a new hybrid of Croston{\textquoteright}s method and Bayesian inference called Hyperbolic-Exponential Smoothing, which is unbiased on non-intermittent and stochastic intermittent demand, decays hyperbolically when obsolescence occurs, and performs well in experiments.",

keywords = "Intermittent demand, Croston{\textquoteright}s method, Bayesian inference",

author = "Steven Prestwich and Tarim, {S Armagan} and Roberto Rossi and Brahim Hnich",

year = "2014",

month = oct,

doi = "10.1016/j.ijforecast.2014.01.006",

language = "English",

volume = "30",

pages = "928--933",

journal = "International Journal of Forecasting",

issn = "0169-2070",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing

AU - Prestwich, Steven

AU - Tarim, S Armagan

AU - Rossi, Roberto

AU - Hnich, Brahim

PY - 2014/10

Y1 - 2014/10

N2 - Croston’s method is generally viewed as being superior to exponential smoothing when the demand is intermittent, but it has the drawbacks of bias and an inability to deal with obsolescence, where the demand for an item ceases altogether. Several variants have been reported, some of which are unbiased on certain types of demand, but only one recent variant addresses the problem of obsolescence. We describe a new hybrid of Croston’s method and Bayesian inference called Hyperbolic-Exponential Smoothing, which is unbiased on non-intermittent and stochastic intermittent demand, decays hyperbolically when obsolescence occurs, and performs well in experiments.

AB - Croston’s method is generally viewed as being superior to exponential smoothing when the demand is intermittent, but it has the drawbacks of bias and an inability to deal with obsolescence, where the demand for an item ceases altogether. Several variants have been reported, some of which are unbiased on certain types of demand, but only one recent variant addresses the problem of obsolescence. We describe a new hybrid of Croston’s method and Bayesian inference called Hyperbolic-Exponential Smoothing, which is unbiased on non-intermittent and stochastic intermittent demand, decays hyperbolically when obsolescence occurs, and performs well in experiments.

KW - Intermittent demand

KW - Croston’s method

KW - Bayesian inference

U2 - 10.1016/j.ijforecast.2014.01.006

DO - 10.1016/j.ijforecast.2014.01.006

M3 - Article

SN - 0169-2070

VL - 30

SP - 928

EP - 933

JO - International Journal of Forecasting

JF - International Journal of Forecasting

IS - 4

ER -

Forecasting Intermittent Demand by Hyperbolic-Exponential Smoothing

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Projects

Confidence-based optimization for inventory management at a local grocery store

Cite this