The Science

A smarter approach to data collection and analysis

Our core technology is based on cutting-edge research and science conducted at the MIT Media Lab.

The four billion mobile phones on the planet are powerful social sensors. As citizens of the information age, we leave digital traces of behavior in our communication and movement patterns.

Ginger.io uses machine learning and data mining to passively collect and analyze subtle signals of behavior change to better understand users' social, physical and mental health status.

“91% of people keep their phone within 3 feet, 24 hours a day.”Morgan StanleyTechnology & Internet Trends

Real-Time Data Collection and Analysis

In order to have meaningful results, you need to have complete data. Traditional data sources provide single intermittent data points. The Ginger.io platform collects and analyzes continuous data to fill in the data gaps, providing a richer, more objective picture of how you're doing.

What happens between data points?
Intermittent Data

Traditional data sources provide single intermittent data points that provide an incomplete view of what's happening.

See a complete picture with Ginger.io
Continuous Passive Data

The Ginger.io platform collects and analyzes continuous data to fill in the data gaps, providing a richer, more objective picture of how you're doing.

Data Science Meets Behavioral Science

Ginger.io taps into the continuous sensor data from your mobile phone and other devices to predict individual behavior changes and identify aggregate trends. Our research from MIT Media Lab demonstrated that location and communication sensors can be used to model individual symptoms and long term health outcomes. This research is at the core of Ginger.io's platform.

Social Sensing to Model Epidemiological Behavior Change

Proceedings of ACM Ubicomp 2010
Madan A., Cebrian M., and Pentland A.

Sensing the “Health State” of a Community

IEEE Pervasive Computing 2012
Madan A., Cebrian M., Moturu S., Farrahi K., and Pentland A.

Social Sensing: Obesity, Unhealthy Eating and Exercise in Face-to-face Networks

Proceedings of ACM Wireless Health 2010
Madan A., Moturu S., Lazer D., and Pentland A.

Using Social Sensing to Understand the Links Between Sleep, Mood, and Sociability

Proceedings of IEEE SocialCom 2011
Moturu S., Khayal I., Aharony N., Pan W., and Pentland A.

Sleep, Mood and Sociability in a Healthy Population

Proceedings of IEEE EMBC 2011
Moturu S., Khayal I., Aharony N., Pan W., and Pentland A.

Pervasive Sensing to Model Political Opinions in Face-to-Face Networks

Pervasive Computing 2011
Madan A., Farrahi K., Gatica-Perez D., and Pentland A.