Volltext-Downloads (blau) und Frontdoor-Views (grau)

Sales forecasting under economic crisis: a case study of the impact of the COVID19 crisis to the predictability of sales of a medium-sized enterprise

  • Forecasting demand is challenging. Various products exhibit different demand patterns. While demand may be constant and regular for one product, it may be sporadic for another, as well as when demand occurs, it may fluctuate significantly. Forecasting errors are costly and result in obsolete inventory or unsatisfied demand. Methods from statistics, machine learning, and deep learning have been used to predict such demand patterns. Nevertheless, it is not clear for what demand pattern, which algorithm would achieve the best forecast. Therefore, even today a large number of models are used to forecast on a test period. The model with the best result on the test period is used for the actual forecast. This approach is computationally and time intensive and, in most cases, uneconomical. In our paper we show the possibility to use a machine learning classification algorithm, which predicts the best possible model based on the characteristics of a time series. The approach was developed and evaluated on a dataset from a B2B-technical-retailer. The machine learning classification algorithm achieves a mean ROC-AUC of 89%, which emphasizes the skill of the model.

Download full text files

  • 3587
    eng

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author of HS ReutlingenGrimm, Florian; Kiefer, Daniel
Editor of HS ReutlingenZimmermann, Alfred
DOI:https://doi.org/10.1007/978-981-16-3264-8_16
ISBN:978-981-16-3264-8
Erschienen in:Human centred intelligent systems : proceedings of KES-HCIS 2021 conference ; Smart innovation, systems and technologies, volume 244
Publisher:Springer
Place of publication:Singapore
Editor:Alfred ZimmermannORCiD, Robert Howlett, Lakhmi Jain, Rainer Schmidt
Document Type:Conference proceeding
Language:English
Publication year:2021
Tag:machine learning; model selection; time series characteristics; univariate time series forecasting
Page Number:10
First Page:163
Last Page:172
DDC classes:004 Informatik
Open access?:Nein
Licence (German):License Logo  In Copyright - Urheberrechtlich geschützt