In this project, we collaborate with a bike rental company. We derive a simulation of customer behavior and test several algorithms for optimizing the distribution of bikes in Copenhagen. In the end, we discover that a Q-learning algorithm can obtain good result in a sufficiently short amount of time.
We find that by using our optimization algorithm, the bike rental company can increase their total weekly rental time by roughly 20%. The company currently plans on testing the algorithm.
|Effective start/end date||01/08/2022 → 31/01/2023|
- Technical University of Denmark (lead)
- Donkey Republic (Project partner)
UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):