Optimising public transport: A data-driven bike-sharing study in Marburg

Martin Lellep

Playlists: 'rc3-2021' videos starting here / audio

Imagine you are running late for your bus and decide to grab a bike-sharing bike to get there in time. More often than not I found myself standing at an empty station only to miss my bus. Here, I present you my data-driven approach to avoid walking to empty bike-sharing stations.

I started collecting Nextbike data in Marburg many months back in order to solve my personal issue of facing empty Nextbike stations in Marburg. After collecting more than 1,000,000 data points, I turned towards the analysis to figure out which stations in Marburg to avoid when desperately needing a bike.

After finding the data-driven solution to that question, I expanded my study to not only answer questions for Nextbike users but also from the perspective of the city council to make the lives of all of us easier, healthier and eco-friendlier. After those statistical statements, I conclude my study with a more precise machine-learning based prediction of parked bikes to motivate data-driven optimisations in public transport.


These files contain multiple languages.

This Talk was translated into multiple languages. The files available for download contain all languages as separate audio-tracks. Most desktop video players allow you to choose between them.

Please look for "audio tracks" in your desktop video player.