AI

Understanding user behavior at three scales: The AGoogleADay story

Abstract

How people behave is the central question for data analytics, and a single approach to understanding user behavior is often limiting. The way people play, the ways they interact, the kinds of behaviors they bring to the game, these factors all ultimately drive how our systems perform, and what we can understand about why users do what they do. I suggest that looking at user data at three different scales of time and sampling resolution shows us how looking at behavior data at the micro-, meso-, and macro levels is a superb way to understand what people are doing in our systems, and why. Knowing this lets you not just understand what’s going on, but also how to improve the user experience for the next design cycle