T-REX: Transformer-Based Category Sequence Generation for Grocery Basket Recommendation

• URL: http://arxiv.org/abs/2603.06631v1
• Date: Mon, 23 Feb 2026 19:19:46 GMT
• Title: T-REX: Transformer-Based Category Sequence Generation for Grocery Basket Recommendation
• Abstract summary: T-REX generates personalized category-level suggestions by learning both short-term basket dependencies and long-term user preferences.<n>Our approach introduces three key innovations: (1) an efficient sampling strategy utilizing dynamic sequence splitting for sparse shopping patterns, (2) an adaptive positional encoding scheme for temporal patterns, and (3) a category-level modeling approach that reduces dimensionality while maintaining recommendation quality.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online grocery shopping presents unique challenges for sequential recommendations due to repetitive purchase patterns and complex item relationships within the baskets. Unlike traditional e-commerce, grocery recommendations must capture both complementary item associations and temporal dependencies across shopping sessions. To address these challenges in Amazon's online grocery business, we propose T-REX, a novel transformer architecture that generates personalized category-level suggestions by learning both short-term basket dependencies and long-term user preferences. Our approach introduces three key innovations: (1) an efficient sampling strategy utilizing dynamic sequence splitting for sparse shopping patterns, (2) an adaptive positional encoding scheme for temporal patterns, and (3) a category-level modeling approach that reduces dimensionality while maintaining recommendation quality. Although masked language modeling techniques like BERT4Rec excel at capturing item relations, they prove less suitable for next basket generation due to information leakage issues. In contrast, T-REX's causal masking approach better aligns with the sequential nature of basket generation, enabling more accurate next-basket predictions. Experiments on large-scale grocery offline data and online A/B tests show significant improvement over existing systems.

Related papers

• REAR: Test-time Preference Realignment through Reward Decomposition [68.09214603569744]
  We introduce a novel framework that models the task as a realignment problem, since the base model often fails to align with the stated preference.<n>We derive a REAlignment Reward (REAR) that selectively rescales the proportions of these two reward terms.<n>We show that REAR can be formulated as a linear combination of token-level policy log-probabilities, making it computationally efficient and easy to integrate with various TTS algorithms.
  arXiv  Detail & Related papers  (2026-06-29T14:17:53Z)
• GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models [31.736819236884827]
  We present a fine-tuned language model for grocery category recommendation in a real-world production environment.<n>GROCLM employs a two-stage LoRA-based training strategy to encode cyclical purchasing patterns directly into model parameters.<n>Experiments on both proprietary production data and a public benchmark demonstrate that GROCLM consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T23:55:15Z)
• GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation [14.663434490160016]
  We present GenRec, a preference-oriented generative framework deployed on the JD App.<n>In month-long online A/B tests, GenRec achieves 9.5% improvement in click count and 8.7% in transaction count over the existing pipeline.
  arXiv  Detail & Related papers  (2026-04-16T11:07:05Z)
• GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search [51.44490997013772]
  GLASS is a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search.<n>We show that GLASS outperforms state-of-the-art baselines in experiments on two large-scale real-world datasets.
  arXiv  Detail & Related papers  (2026-02-05T13:48:33Z)
• Generative Sequential Recommendation via Hierarchical Behavior Modeling [20.156854767000475]
  We propose a novel generative framework, GAMER, built upon a decoder-only backbone.<n> GAMER introduces a cross-level interaction layer to capture hierarchical dependencies among behaviors.<n>ShortVideoAD is a large-scale multi-behavior dataset from a mainstream short-video platform.
  arXiv  Detail & Related papers  (2025-11-05T03:27:01Z)
• Grocery to General Merchandise: A Cross-Pollination Recommender using LLMs and Real-Time Cart Context [3.407794744126759]
  This paper introduces a cross-pollination (XP) framework that bridges grocery and general merchandise cross-category recommendations.<n>Our solution employs a two-stage framework: (1) A candidate generation mechanism that uses co-purchase market basket analysis and LLM-based approach to identify novel item-item associations; and (2) a transformer-based ranker that leverages the real-time sequential cart context.<n> offline analysis and online A/B tests show an increase of 36% add-to-cart rate with LLM-based retrieval on the item page, and 15% lift in add-to-cart using cart context-
  arXiv  Detail & Related papers  (2025-09-02T23:28:34Z)
• A Generative Re-ranking Model for List-level Multi-objective Optimization at Taobao [20.11584617315975]
  We propose a novel end-to-end generative re-ranking model named Sequential Ordered Regression Transformer-Generator (SORT-Gen) for the less-studied list-level multi-objective optimization problem.<n>SORT-Gen has been successfully deployed in multiple scenarios of Taobao App, serving for a vast number of users.
  arXiv  Detail & Related papers  (2025-05-12T03:01:14Z)
• Pre-training Generative Recommender with Multi-Identifier Item Tokenization [78.87007819266957]
  We propose MTGRec to augment token sequence data for Generative Recommender pre-training.<n>Our approach involves two key innovations: multi-identifier item tokenization and curriculum recommender pre-training.<n>Extensive experiments on three public benchmark datasets demonstrate that MTGRec significantly outperforms both traditional and generative recommendation baselines.
  arXiv  Detail & Related papers  (2025-04-06T08:03:03Z)
• MMGRec: Multimodal Generative Recommendation with Transformer Model [81.61896141495144]
  MMGRec aims to introduce a generative paradigm into multimodal recommendation. We first devise a hierarchical quantization method Graph CF-RQVAE to assign Rec-ID for each item from its multimodal information. We then train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences.
  arXiv  Detail & Related papers  (2024-04-25T12:11:27Z)
• Low-Rank Online Dynamic Assortment with Dual Contextual Information [12.373566593905792]
  We introduce a new low-rank dynamic assortment model to transform this problem into a manageable scale. We then propose an efficient algorithm that estimates the intrinsic subspaces and utilizes the upper confidence bound approach to address the exploration-exploitation trade-off in online decision making.
  arXiv  Detail & Related papers  (2024-04-19T23:10:12Z)
• Hypergraph Enhanced Knowledge Tree Prompt Learning for Next-Basket Recommendation [50.55786122323965]
  Next-basket recommendation (NBR) aims to infer the items in the next basket given the corresponding basket sequence. HEKP4NBR transforms the knowledge graph (KG) into prompts, namely Knowledge Tree Prompt (KTP), to help PLM encode the Out-Of-Vocabulary (OOV) item IDs. A hypergraph convolutional module is designed to build a hypergraph based on item similarities measured by an MoE model from multiple aspects.
  arXiv  Detail & Related papers  (2023-12-26T02:12:21Z)
• Contrastive Self-supervised Sequential Recommendation with Robust Augmentation [101.25762166231904]
  Sequential Recommendationdescribes a set of techniques to model dynamic user behavior in order to predict future interactions in sequential user data. Old and new issues remain, including data-sparsity and noisy data. We propose Contrastive Self-Supervised Learning for sequential Recommendation (CoSeRec)
  arXiv  Detail & Related papers  (2021-08-14T07:15:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.