Wednesday, November 20, 2013
UR, Room 601
MyBehavior: Automating Personalized Health Feedback Using a Multiarm Bandit Model
In this work, we propose MyBehavior, a mobile application with a suggestion engine that learns a userís physical activity and dietary behavior, and provides finely-tuned personalized suggestions. To our knowledge, MyBehavior is the first smartphone app to provide personalized health suggestions automatically, going beyond commonly used one-size-fits-all prescriptive approaches, or tailored interventions from healthcare professionals. MyBehavior uses an online multi-armed bandit model to automatically generate context-sensitive and personalized activity/food suggestions by learning the userís actual behavior. The app continually adapts its suggestions by exploiting the most frequent healthy behaviors, while sometimes exploring non-frequent behaviors, in order to maximize the userís chance of reaching a health goal (e.g. weight loss).
We evaluated MyBehavior with a three-week deployment and found that personalized suggestions were more effective and easier to incorporate in usersí daily lives, compared to its generic, prescriptive counterpart.
Mashfiqui Rabbi is a PhD student in the Information Science department at Cornell University, where he is working with Tanzeem Choudhury. Mashfiqui's research lies in the intersection of mobile computing, behavior change and activity recognition. His current research aims to build personalized models of physical and mental well-being from off-the-shelf mobile phone sensor data, and subsequently develop targeted interventions that respect user's ability and context.
Mashfiqui's works previously appeared in Ubicomp, Pervasive health, Wireless health, CHI workshops, and Annals of Family Medicine. Mashfiqui transferred to Cornell after spending two eventful years as a PhD student at Dartmouth College. Before starting his PhD, Mashfiqui received Bachelor degree in Computer Science and Engineering from Bangladesh University of Engineering and Technology in 2008, and worked for two years in financial computing at Stochastic Logic Ltd.