University of Twente Student Theses
Demand forecasting at TKH Logistics : Improving alignment of staff and workload schedules at the order picking department of TKH Logistics by developing a forecasting model using time series methods.
Blom, J.J. van der (2025) Demand forecasting at TKH Logistics : Improving alignment of staff and workload schedules at the order picking department of TKH Logistics by developing a forecasting model using time series methods.
|
PDF
10MB |
| Abstract: | This research for TKH Logistics addresses inefficiencies in the order picking division caused by misaligned staff and workload schedules, rooted in unreliable demand forecasting. Using over three years of historical order line data, a customer-level forecasting model was developed with daily granularity and a 20-day horizon. The model incorporates weekly, yearly, and holiday patterns to enhance accuracy and leverages order overview information provided by certain customers. An implementation plan supports adoption, aiming to foster a more controlled and efficient operations environment. The proposed NeuralProphet model significantly outperformed the current forecasting approach, achieving average reductions over a 7-day horizon of 64.8% in MWAPE, 92.9% in bias, and 27.4% in MAD, as validated through time series cross-validation over a 13-week test period. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 58 process technology, 85 business administration, organizational science |
| Programme: | Industrial Engineering and Management BSc (56994) |
| Link to this item: | https://purl.utwente.nl/essays/106519 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page