Daily retail demand forecasting using machine learning with emphasis on calendric special days


Huber, Jakob ; Stuckenschmidt, Heiner



DOI: https://doi.org/10.1016/j.ijforecast.2020.02.005
URL: https://www.sciencedirect.com/science/article/abs/...
Additional URL: https://www.researchgate.net/publication/340794599...
Document Type: Article
Year of publication: 2020
The title of a journal, publication series: International Journal of Forecasting
Volume: 36
Issue number: 4
Page range: 1420-1438
Place of publication: Amsterdam [u.a.]
Publishing house: Elsevier
ISSN: 0169-2070
Publication language: English
Institution: School of Business Informatics and Mathematics > Praktische Informatik II (Stuckenschmidt 2009-)
Subject: 004 Computer science, internet
Abstract: Demand forecasting is an important task for retailers as it is required for various operational decisions. One key challenge is to forecast demand on special days that are subject to vastly different demand patterns than on regular days. We present the case of a bakery chain with an emphasis on special calendar days, for which we address the problem of forecasting the daily demand for different product categories at the store level. Such forecasts are an input for production and ordering decisions. We treat the forecasting problem as a supervised machine learning task and provide an evaluation of different methods, including artificial neural networks and gradient-boosted decision trees. In particular, we outline and discuss the possibility of formulating a classification instead of a regression problem. An empirical comparison with established approaches reveals the superiority of machine learning methods, while classification-based approaches outperform regression-based approaches. We also found that machine learning methods not only provide more accurate forecasts but are also more suitable for applications in a large-scale demand forecasting scenario that often occurs in the retail industry.

Dieser Eintrag ist Teil der Universitätsbibliographie.




+ Citation Example and Export

Huber, Jakob ; Stuckenschmidt, Heiner ORCID: 0000-0002-0209-3859 (2020) Daily retail demand forecasting using machine learning with emphasis on calendric special days. International Journal of Forecasting Amsterdam [u.a.] 36 4 1420-1438 [Article]


+ Search Authors in

BASE: Huber, Jakob ; Stuckenschmidt, Heiner

Google Scholar: Huber, Jakob ; Stuckenschmidt, Heiner

ORCID: Huber, Jakob ; Stuckenschmidt, Heiner ORCID: 0000-0002-0209-3859

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item