University of Twente Student Theses
Driving last-mile delivery efficiency at Picnic by predicting travel times
Plomp, M.A. (2024) Driving last-mile delivery efficiency at Picnic by predicting travel times.
|
PDF
4MB |
| Abstract: | This research was conducted at Picnic Technologies, an e-grocer operating in The Netherlands, Germany, and France. Our focus is on optimizing last-mile delivery by accurately predicting drive times between customer stops. We aim to enhance the planning accuracy of these drive times to improve key business performance indicators: on-time delivery percentage and minutes per delivery. We propose a solution design involving the construction and comparison of various prediction models, such as common machine learning techniques and a linear regression. These models incorporate location and timing features, and modify drive time estimates sourced from an external company. The neural network turned out to have the highest predictive performance, and with this model we learned the impact on the main business KPIs. |
| Item Type: | Essay (Master) |
| Clients: | Picnic Technologies, Amsterdam, Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 31 mathematics |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/100242 |
| 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