Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation

2026-05-01

AI Summary

This work addresses the limitations of existing next-basket recommendation methods, which often fail to distinguish between users’ intent to repurchase familiar items and their desire to explore new interests, while also neglecting inter-purchase time intervals and item-specific temporal periodicity. To overcome these issues, the authors propose TIDE, a novel model that explicitly decouples these dual intents for the first time in this task. TIDE employs a dual-expert architecture to separately model habitual repurchasing and exploratory behavior, combined with an item-aware gating mechanism that dynamically fuses the two signals. Furthermore, it introduces a Hawkes-enhanced Fourier temporal encoding to capture item-level periodic patterns and decay dynamics over continuous time. Extensive experiments on four real-world datasets demonstrate that TIDE significantly outperforms state-of-the-art baselines, confirming its effectiveness in improving recommendation accuracy.

Abstract

Next-basket recommendation (NBR) is a type of recommendation that aims to predict a set of items a user will purchase based on their historical transaction basket sequences. It is governed by a dynamic interplay between two distinct user intents: habitual repurchase, which involves repeating past behaviors, and exploratory interest, which involves discovering new items. However, existing NBR methods generally suffer from two limitations: (1) they often entangle these conflicting motives within a single representation, causing habits to overshadow discovery, and (2) they rely on discrete sequential modeling that ignores continuous-time intervals and item-specific periodicities. In this paper, we propose a novel solution named Time-Interval Disentangled Experts (TIDE) to address these challenges. TIDE incorporates a Hawkes-enhanced Fourier Time Encoding to capture item-specific temporal periodicities and dynamic decay. To decouple user intentions, TIDE utilizes a dual-expert architecture that integrates a Habit Expert for recurring needs and a Pattern-Guided Exploration Expert for discovery. Combined with an item-aware gating mechanism, TIDE adaptively balances repurchase and exploration. Extensive experiments on four diverse real-world datasets demonstrate that TIDE consistently outperforms representative state-of-the-art NBR methods.

Problem

• next-basket recommendation
• user intent disentanglement
• time intervals
• temporal periodicity
• habit vs. exploration

Innovation

• disentangled representation
• time-interval modeling
• next-basket recommendation
• dual-expert architecture
• temporal periodicity