📢 Dear colleagues working on human mobility modeling and prediction -- we are excited to announce a new open dataset of human mobility which contains city-scale, longitudinal, anonymized, 100,000 individual mobility trajectories. Scientific Data: nature.com/articles/s4159…

This project was motivated by the lack of open-source, standardized, and accessible human mobility datasets. This hinders fair comparisons and reproducibility of ML/AI algorithms for next-place-prediction tasks, which is a popular problem in Geospatial ML and AI.

Hopefully this dataset can help the community push forward fair, reproducible, and equitable research efforts. This was joint work with Yahoo Japan (Kota Tsubouchi, Toru Shimizu), MIT (Esteban Moro, Alex Pentland), and the University of Tokyo (Yoshihide Sekimoto, Kaoru Sezaki).

The dataset can be accessed through Zenodo without any registration: zenodo.org/records/108362…

We held a data challenge last year. We are thinking of hosting the next edition later this year. Let's connect if you're interested! 🎉
connection.mit.edu/humob-challeng…

Please spread the word!