University of Twente Student Theses
Developing a shipment forecast for carriers, by incorporating uncertainty factors through the utilization of machine learning methods : Research for creating a shipment volume forecast for the overseas carriers and freight forwarders
Bosscher, F.D. (2023) Developing a shipment forecast for carriers, by incorporating uncertainty factors through the utilization of machine learning methods : Research for creating a shipment volume forecast for the overseas carriers and freight forwarders.
|
PDF
2MB |
| Abstract: | Research in developing a carrier shipment forecast, that uses the order information of suppliers in combination with the (expected) packaging information. Based on the different methods in the literature, we make a combination of multiple models to create one flow of forecasting. This forecasting flow consists of 10 steps and makes a distinction between the deterministic and stochastic part. We assessed the lead time variability by comparing the differences between the planned and actual delivery dates for each supplier. To calculate the shipment volumes accurately, we multiplied them by the expected proportions for each week of shipment. To account for the frozen period in the forecast, we multiply the shipment volumes by the proportions in which week the shipment is expected. By testing four ML methods to predict the shipment volumes for the non-Scania packaging suppliers, the LightGBM exhibits the highest accuracy among the methods. This forecast determines the total volume (expressed in cubic meters, which can be converted to the number of containers) that carriers need to transport. The forecast is used to provide insights and pre-book the required transport capacity at the carriers in advance, such that the freight shipped on spot market rates is minimized. |
| Item Type: | Essay (Master) |
| Clients: | Scania Logistics Netherland, Zwolle, Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 58 process technology |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/96477 |
| 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