TY - CHAP U1 - Konferenzveröffentlichung A1 - Kiefer, Daniel A1 - Bauer, Markus A1 - Grimm, Florian ED - Zimmermann, Alfred ED - Howlett, Robert ED - Jain, Lakhmi ED - Schmidt, Rainer T1 - Univariate time series forecasting: machine learning prediction of the best suitable forecast model based on time series characteristics T2 - Human centred intelligent systems : proceedings of KES-HCIS 2021 conference ; Smart innovation, systems and technologies, volume 244 N2 - 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. KW - univariate time series forecasting KW - time series characteristics KW - machine learning KW - model selection Y1 - 2021 SN - 978-981-16-3266-2 SB - 978-981-16-3266-2 U6 - https://doi.org/10.1007/978-981-16-3264-8_15 DO - https://doi.org/10.1007/978-981-16-3264-8_15 SP - 152 EP - 162 S1 - 11 PB - Springer CY - Singapore ER -