TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Kiefer, Daniel
A1  - Grimm, Florian
A1  - van Dinther, Clemens
T1  - Artificial intelligence in supply chain management: investigation of transfer learning to improve demand forecasting of intermittent time series with deep learning
T2  - Proceedings of the 55th Hawaii International Conference on System Sciences (HICSS 2022), 4-7 January 2022, virtual event/Maui
N2  - Demand forecasting intermittent time series is a challenging business problem. Companies have difficulties in forecasting this particular form of demand pattern. On the one hand, it is characterized by many non-demand periods and therefore classical statistical forecasting algorithms, such as ARIMA, only work to a limited extent. On the other hand, companies often cannot meet the requirements for good forecasting models, such as providing sufficient training data. The recent major advances of artificial intelligence in applications are largely based on transfer learning. In this paper, we investigate whether this method, originating from computer vision, can improve the forecasting quality of intermittent demand time series using deep learning models. Our empirical results show that, in total, transfer learning can reduce the mean square error by 65 percent. We also show that especially short (65 percent reduction) and medium long (91 percent reduction) time series benefit from this approach.
KW  - transfer learning
KW  - intermittent time series
KW  - demand forecasting
KW  - deep learning
KW  - artificial intelligence
Y1  - 2022
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-38719
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-38719
UR  - http://hdl.handle.net/10125/79537
SN  - 978-0-9981331-5-7
SB  - 978-0-9981331-5-7
SP  - 1656
EP  - 1665
S1  - 10
PB  - University of Hawai'i at Manoa
CY  - Honolulu
ER  -