Harnessing the Small Victories: Empirical Evidence from a Calorie and Weight Loss Tracking Application

• Activity Number: 384 - Artificial Intelligence Meets Behavioral Science: Innovations in Discovering and Leveraging Nudges
• Type: Invited
• Date/Time: Tuesday, July 30, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Marketing
• Author(s): Kosuke Uetake and Nathan Yang*
• Companies: Yale University and McGill University
• Keywords: Customer development; Gamification; Goal design; Machine learning; Mobile application; Precision health retail

Abstract

We investigate the role of small victories, in the form of short-term goal achievements, on long-term health outcomes. Using novel large-scale data from a popular mobile calorie and weight management application, we track the daily health outcomes across a large number of users. The application sets a salient daily budget for calories, and by comparing cases in which the user is slightly under or over-budget, we first document empirical patterns between small victories and various long-term weight-loss outcomes. Motivated by these patterns, we estimate a dynamic structural model of calorie consumption with reference-dependent utility to evaluate various hypothetical goal design schemes. Counterfactual analysis of the estimated model reveal that adaptive goals are better at balancing long-run utility and disciplined calorie consumption.