an open-source Python toolbox to analyze mobile phone metadata

Get started > Test it >

May 6st, 2016 > we released a new version (0.5) which includes an interactive visualization, support for mobile phone recharges, support for Python 3, and clustering algorithms to handle both antenna and GPS locations. The computations are significantly faster and the memory footprint is reduced. This release is available on GitHub and PyPI.

Data visualization

bandicoot has built-in visualization tools. Load a user's file and visualize his social graph, mobility pattern, and interactions.

Check out our IPython notebook for live examples.

Data verification

We detect and warn you of potential missing data (no location, wrong date…). bandicoot automatically exports more than 40 reporting metrics to help you detect issues.

Bandicoot interactive visualization
Bandicoot Android application

Try bandicoot on your phone

Our Android application let you export all your call and text logs into a CSV file. This file can then be imported into the bandicoot toolbox for analysis and visualization.

They use bandicoot

ENS de Lyon
You Technology

Research papers

Predicting Personality Using Novel Mobile Phone-Based Metrics
Big Data-Driven Marketing: How machine learning outperforms marketers' gut-feeling
Predicting Gender from Mobile Phone Metadata
Mobility profiles and calendars for food security and livelihoods analysis
Using Deep Learning to Predict Demographics from Mobile Phone Metadata

If you use bandicoot in your research please cite it as: de Montjoye, Y. A., Rocher, L., & Pentland, A. S. (2016). bandicoot: a Python Toolbox for Mobile Phone Metadata. Journal of Machine Learning Research, 17(175), 1-5.

Our team

Yves-Alexandre de Montjoye

Imperial College London

Luc Rocher

Université catholique de Louvain

Alex ‘Sandy’ Pentland

MIT Media Lab

As well as Florent Robic, Kevin Mustelier, Walter Menendez, Zachary Neeley, Keeley Erhardt, William Navarre, Brian Sweatt, and Bjarke Felbo.


Sign-up to our newsletter to receive updates (2-3 times a year) about bandicoot.


Feel free to ask questions and report issues on our GitHub page or to contact us at where Y=bandicoot.