An Adaptive, Data-Driven Personalized Advisor for Increasing Physical Activity.

In recent years, there has been growing interest in the use of fitness trackers and smartphone applications for promoting physical activity. Most of these applications use accelerometers to measure the level of activity that users engage in and provide descriptive, interactive reports of a user's step counts. While these reports are data-driven and personalized, any recommendations, if provided, are limited to popular health advice. In our work, we develop an approach for providing data-driven and personalized recommendations for intraday activity planning. We generate an hour-by-hour activity plan that is informed by the user's probability of adhering to the plan. The user's probability of adherence to the plan is personalized, based on his/her past activity patterns and current activity target. Using this approach, we can tailor notifications (e.g., reminders, encouragement) based on the user's adherence to the plan. We can also dynamically update the user's activity plan mid-day, if his/her actual activity deviates sufficiently from the original plan such that the original plan becomes unrealistic for the user to achieve. In this paper we describe an implementation of our approach and report our technical findings with respect to identifying typical activity patterns from historical data, predicting whether an activity target will be achieved, and adapting an activity plan based on a user's actual performance throughout the day.