Fair household food recommendations balance diets and shared pantry use
FairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food Recommendation
Artificial IntelligenceComputer Science and Game Theory
Summary
Households face the problem of recommending food that suits everyone’s diets while sharing limited pantry space. The authors present FairFRESH, a framework that learns individual food preferences, respects dietary rules, and fairly divides shared food among household members. It also explains why each food is recommended using attribution methods. Their system improves fairness in food recommendations and pantry use on real and simulated data, while meeting dietary needs and showing clear explanations.
What this means in practice
- •For smart home developers: Design smart kitchen assistants that recommend meals balancing dietary preferences and shared pantry constraints for multiple household members.
- •For meal kit providers: Improve meal kit delivery by optimizing fair and diet-compliant food allocations for families sharing limited ingredients.$Commercial implications: Enables personalized, fair meal planning for households, enhancing product appeal and reducing waste.
Authors
Kodur Sai Vinay Sathvik, Kakoli Bora, Tejaswini R. M
Abstract
Recommender systems typically serve one user at a time. However, in households, members share a finite pantry and follow different dietary rules, making independent recommendations prone to resource conflicts and dietary violations. We formulate household food recommendation as constrained fair division and present FairFRESH, a neuro-symbolic framework that learns per-member utilities, allocates foods under explicit welfare objectives, enforces dietary rules through a deterministic filter, and explains recommendations using Shapley and Banzhaf attributions. Theoretically, we show that no finite penalty guarantees compliance near a dietary-rule threshold, establish approximation guarantees for greedy allocation under utilitarian and smoothed Nash objectives in the stock-free model before filtering, and characterize the scale invariance of Nash welfare. We also use the minimax theorem to analyze rotating shared meals. On NHANES-derived data, the learned utility model achieves Recall@20 of 0.293, outperforming five learned recommenders (at most 0.244) but not a previous-day repetition heuristic (0.321). On held-out four-person households, Nash allocation reduces Gini disparity by 42% relative to conflict resolution while improving Recall@20 from 0.180 to 0.197. It comes within 2% of an upper bound on the smoothed Nash optimum, and rescaling one member's utilities changes at most 1.5% of assignments. All recommendations satisfy the encoded dietary rules, while attribution scores correlate with utility loss upon component removal (r = 0.76). In simulation, shared meals reduce pantry use by about one-third, and weekly rotation increases the worst-off member's utility by 38% over the best fixed meal.