CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation

TL;DR

CASE introduces a cadence-aware set encoding approach for large-scale next basket recommendation, explicitly modeling item purchase timing and improving prediction accuracy in industrial-scale retail settings.

Contribution

It presents a scalable, cadence-aware model that decouples item-level timing from cross-item interactions, enabling explicit calendar-time modeling in recommendation systems.

Findings

CASE improves precision, recall, and NDCG on public benchmarks.

It achieves up to 8.6% relative precision lift in industrial-scale evaluation.

The model effectively captures recurring purchase rhythms across datasets.

Abstract

Repurchase behavior is a primary signal in large-scale retail recommendation, particularly in categories with frequent replenishment: many items in a user's next basket were previously purchased, and their timing follows stable, item-specific cadences. Yet most next basket repurchase recommendation models represent history as a sequence of discrete basket events indexed by visit order, which cannot explicitly model elapsed calendar time or update item rankings as days pass between purchases. We present CASE (Cadence-Aware Set Encoding) for next basket repurchase recommendation, which decouples item-level cadence learning from cross-item interaction, enabling explicit calendar-time modeling while remaining production-scalable. CASE represents each item's purchase history as a calendar-time signal over a fixed horizon, applies shared multi-scale temporal convolutions to capture recurring rhythms, and uses induced set attention to model cross-item dependencies with sub-quadratic complexity, allowing efficient batch inference at scale. Across three public benchmarks and a proprietary dataset, CASE consistently improves precision, recall, and NDCG at multiple cutoffs compared to strong next basket recommendation baselines. In a production-scale evaluation with tens of millions of users and a large item catalog, CASE achieves up to 8.6% relative precision lift and 9.9% relative recall lift at top-5, showing that scalable cadence-aware modeling yields measurable gains in both benchmark and industrial settings.