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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Yanan, Ranjan, Ashish, Subramaniam, Sinduja, Korpeoglu, Evren, Nag, Kaushiki, Achan, Kannan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917436160212992
author Cao, Yanan
Ranjan, Ashish
Subramaniam, Sinduja
Korpeoglu, Evren
Nag, Kaushiki
Achan, Kannan
author_facet Cao, Yanan
Ranjan, Ashish
Subramaniam, Sinduja
Korpeoglu, Evren
Nag, Kaushiki
Achan, Kannan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06718
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation
Cao, Yanan
Ranjan, Ashish
Subramaniam, Sinduja
Korpeoglu, Evren
Nag, Kaushiki
Achan, Kannan
Information Retrieval
Machine Learning
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.
title CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2604.06718