Nathan Eagle at Social Graph Foo Camp, February 2008
summary
Gives out 100 phones running invisible logging software that records calls, SMS and continuous Bluetooth proximity, plus fixed Bluetooth beacons called blar across campus. Builds hidden Markov models to extract daily routines and predict meetings and lunches, and infers social ties from proximity with 96% accuracy. Detects organizational rhythms (late nights before sponsor week), crowd movements (downtown after a sports upset) and walking speed changes tied to finals and breaks.
AI-written summary · about
related talks
26m"Reality Mining for Compan
08mon the Emerging Technologies He's Working On
46mLow Friction Personal Data Collection
29mSara Hooker & Sean McPherson, Delta Analytics at MLconf Seattle 2017
23mAnalysis of Privacy Protections in Fitness Tracking Social Networks -or- You can run, but can you hide?
08mEvil Uses of Data
21mThinkActive: Designing for Pseudonymous Activity Tracking in the Classroom
29mBuilding an Invisible App