Translating Dietary Standards into Healthy Meals with Minimal Substitutions

TL;DR

This paper introduces an end-to-end framework that generates healthy, affordable meals with minimal substitutions by translating dietary standards into realistic meal options, improving nutritional adherence and reducing costs.

Contribution

It presents a novel generative model conditioned on meal archetypes to produce compliant, cost-effective meals with minimal changes, advancing personalized diet systems.

Findings

Generated meals follow RDI targets 47% better than baseline

Meals are 10% more nutritious with 1-3 substitutions

Cost reductions of 19-32% achieved on average

Abstract

An important goal for personalized diet systems is to improve nutritional quality without compromising convenience or affordability. We present an end-to-end framework that converts dietary standards into complete meals with minimal change. Using the What We Eat in America (WWEIA) intake data for 135,491 meals, we identify 34 interpretable meal archetypes that we then use to condition a generative model and a portion predictor to meet USDA nutritional targets. In comparisons within archetypes, generated meals are better at following recommended daily intake (RDI) targets by 47.0%, while remaining compositionally close to real meals. Our results show that by allowing one to three food substitutions, we were able to create meals that were 10% more nutritious, while reducing costs 19-32%, on average. By turning dietary guidelines into realistic, budget-aware meals and simple swaps, this framework can underpin clinical decision support, public-health programs, and consumer apps that deliver scalable, equitable improvements in everyday nutrition.