S2SRec2: Set-to-Set Recommendation for Basket Completion with Recipe

TL;DR

This paper introduces S2SRec2, a novel set-to-set recommendation framework that predicts multiple complementary ingredients for incomplete baskets, leveraging recipe knowledge and a multitask learning approach to improve grocery shopping and meal creation.

Contribution

It reformulates basket completion as a set-to-set problem and develops a Set Transformer-based model trained with multitask learning, addressing limitations of traditional single-ingredient prediction methods.

Findings

Outperforms baseline methods on large-scale recipe datasets

Effectively predicts multiple complementary ingredients

Enhances culinary creativity and grocery shopping experience

Abstract

In grocery e-commerce, customers often build ingredient baskets guided by dietary preferences but lack the expertise to create complete meals. Leveraging recipe knowledge to recommend complementary ingredients based on a partial basket is essential for improving the culinary experience. Traditional recipe completion methods typically predict a single missing ingredient using a leave-one-out strategy. However, they fall short in two key aspects: (i) they do not reflect real-world scenarios where multiple ingredients are often needed, and (ii) they overlook relationships among the missing ingredients themselves. To address these limitations, we reformulate basket completion as a set-to-set (S2S) recommendation problem, where an incomplete basket is input into a system that predicts a set of complementary ingredients. We introduce S2SRec2, a set-to-set ingredient recommendation framework based on a Set Transformer and trained in a multitask learning paradigm. S2SRec2 jointly learns to (i) retrieve missing ingredients from the representation of existing ones and (ii) assess basket completeness after prediction. These tasks are optimized together, enforcing accurate retrieval and coherent basket completion. Experiments on large-scale recipe datasets and qualitative analyses show that S2SRec2 significantly outperforms single-target baselines, offering a promising approach to enhance grocery shopping and inspire culinary creativity.