Quality Diversity for Reliable Data Driven Time-Use Optimization

2026-08-05

AI Summary

This study addresses a critical limitation in traditional time allocation optimization for health interventions, which typically maximizes expected health benefits while ignoring prediction uncertainty, often yielding impractical recommendations. To overcome this, the work introduces a novel approach that, for the first time, integrates prediction uncertainty into a quality-diversity (QD) optimization framework. By combining compositional data analysis with multi-objective optimization, it proposes a dual behavior representation—capturing both variable- and objective-level characteristics—to explicitly model the relationship between time allocation and health outcomes under uncertainty. Evaluated on a cohort of over one thousand children, the proposed method generates daily activity schedules that simultaneously achieve high health benefits, low prediction uncertainty, and high diversity, thereby substantially enhancing the reliability and practicality of behavioral interventions.

Abstract

The daily allocation of the finite 24-hour time budget is strongly associated with physical, mental, and cognitive health. While predictive models can estimate the relationship between time-use compositions and health outcomes such as body mass index, life satisfaction, and cognition, most optimization approaches focus only on maximizing expected benefit and do not consider the uncertainty inherent in data-driven prediction. Ignoring uncertainty in health-related decisions can lead to unrealistic time-use recommendations. To address this gap, we introduce an uncertainty quantification Quality Diversity (QD) framework for a more reliable time-use recommendation. Objective functions are derived using compositional data analysis using a large child cohort dataset n > 1000, to capture the relationship between daily activity compositions and multiple health indicators. We develop a new approach that incorporates predictive uncertainty into QD processes and produces more reliable recommendations that balance the expected health benefits with the confidence of the model. We explore the solution space through variable-based and objective-based behavioral representations, revealing diverse high-quality time-use composition and explicit relationships between health outcomes under uncertainty. By embedding uncertainty directly into optimization, our framework shifts the time-use recommendations toward regions of lower uncertainty while preserving high-quality structures for more reliable decision-making in behavioral health.

Problem

• time-use optimization
• predictive uncertainty
• health outcomes
• compositional data
• reliable recommendations

Innovation

• Quality Diversity
• Uncertainty Quantification
• Time-Use Optimization
• Compositional Data Analysis
• Behavioral Health