Learning algorithm with a pilot deployment · 2020
Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
Liao P, Greenewald K, Klasnja P, Murphy S
What it found
An algorithm that learns, for each person, when a suggestion is worth sending, improving as their data comes in. In the HeartSteps app it decided up to five times a day whether to send an activity suggestion.
Where the evidence stops
An algorithm paper with a small pilot; not a trial of outcomes.
How it shapes Pursue
Pursue
Personalisation should be learned for each person over time, not copied from everyone else.
A design input, not evidence that Pursue works.