BEACON: Balancing Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes

TL;DR

BEACON tackles the challenge of recommending complete meal plans that balance nutritional value and convenience over multiple days. It defines a formal problem over inputs $ (\\mathcal{R}, \\mathcal{U}, \\mathcal{C}) $ and proposes a dataset of $50$ $R3$ recipes converted from fast-food menus via GPT-3.5 and human curation, plus a goodness metric combining $md$, $cs$, and $uc$, with a composite score $G$. It introduces a Relational Boosted Bandit $M2$ method and demonstrates superior performance on $uc$ and $cs$ across simulated time horizons $t_1$, $t_2$, $t_3$ and varied user configurations, relative to baselines $M0$ and $M1$. The work provides a practical pathway toward scalable, constraint-aware, long-term meal recommendations and suggests future work on expanding $R3$ coverage and feature sets.

Abstract

A common, yet regular, decision made by people, whether healthy or with any health condition, is to decide what to have in meals like breakfast, lunch, and dinner, consisting of a combination of foods for appetizer, main course, side dishes, desserts, and beverages. However, often this decision is seen as a trade-off between nutritious choices (e.g., low salt and sugar) or convenience (e.g., inexpensive, fast to prepare/obtain, taste better). In this preliminary work, we present a data-driven approach for the novel meal recommendation problem that can explore and balance choices for both considerations while also reasoning about a food's constituents and cooking process. Beyond the problem formulation, our contributions also include a goodness measure, a recipe conversion method from text to the recently introduced multimodal rich recipe representation (R3) format, and learning methods using contextual bandits that show promising results.

Figures (1)

• Figure 1: A brief depiction of BEACON's architecture.