University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

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.

[img] 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

 

Repository Staff Only: item control page