University of Cambridge > Talks.cam > Computer Laboratory Wednesday Seminars > Data Science for the World of Moving Things

Data Science for the World of Moving Things

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact David Greaves.

Trains, buses, taxis, cars, deliveries. These exist in three networks simultaneously: the physical network of roads and train lines, the data network of sensing and analytics and control, and the social network of people who make use of them.

I will tell the story of a data science startup, where my colleagues and I spent five years making sense of these networks. We started with incentive schemes, paying and persuading commuters to shift their habits. We moved on to dashboards and full-resolution reconstruction of the transit network, to see where there was congestion and whom we needed to target. We built a new type of database, for rich and high-speed processing of spacetime data; and we designed a visual querying language to make the system accessible to urban planners and transit agencies. And, in the end, we joined the Google Maps team.

We learnt some hard lessons about how to interact with data visually and tangibly. I believe that over the next decade it will become easy to understand and argue with big datasets, as easy as Excel is today; and I will discuss the way ahead.

This talk is part of the Computer Laboratory Wednesday Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity