In Jurassic Park, scientists mined dino DNA from mosquitoes trapped in fossilized amber. But before they could use that DNA to clone a dinosaur, there was a catch: the sequences were damaged and incomplete. Ultimately, they needed frog DNA to infer the missing gaps to get a complete DNA sequence to clone dinosaurs.

The Jawbone UP system captures health data through a battery of sensors on your wrist and app on your phone -- your movement, sleep, and heart rate. But this data is often incomplete and noisy, and most of the raw signals by themselves aren’t useful. How can we take this data and turn it into health insights, or motivation? Or achieve the ultimate goal of helping our customers live healthier lives? How much treatment is too much -- when do people want to just see their data, even though it’s flawed and incomplete?

With domain expertise (generative models), Bayesian techniques, and external data sources, we can fill in the gaps just like Jurassic Park scientists to get a complete picture of your health. In this talk, learn how applied machine learning techniques and data science helped Jawbone build the best and smartest fitness tracking app.