NudgeRank: Digital Algorithmic Nudging for Personalized Health
This work addresses health behavior change for a large population, representing a significant enterprise deployment but is incremental as it builds on existing nudging and recommendation techniques.
The paper tackles the problem of promoting positive health behaviors at scale by developing NudgeRank, a digital algorithmic nudging system that achieved a 6.17% increase in daily steps and a 7.61% rise in exercise minutes for over 1.1 million users daily.
In this paper we describe NudgeRank, an innovative digital algorithmic nudging system designed to foster positive health behaviors on a population-wide scale. Utilizing a novel combination of Graph Neural Networks augmented with an extensible Knowledge Graph, this Recommender System is operational in production, delivering personalized and context-aware nudges to over 1.1 million care recipients daily. This enterprise deployment marks one of the largest AI-driven health behavior change initiatives, accommodating diverse health conditions and wearable devices. Rigorous evaluation reveals statistically significant improvements in health outcomes, including a 6.17% increase in daily steps and 7.61% more exercise minutes. Moreover, user engagement and program enrollment surged, with a 13.1% open rate compared to baseline systems' 4%. Demonstrating scalability and reliability, NudgeRank operates efficiently on commodity compute resources while maintaining automation and observability standards essential for production systems.