RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph

TL;DR

This paper introduces RETE, a retrieval-enhanced framework for temporal event forecasting on a unified query-product graph, effectively capturing dynamic user preferences and improving behavior prediction in e-commerce.

Contribution

The paper proposes a novel retrieval-based method, RETE, that dynamically extracts relevant subgraphs for user representation, addressing data scarcity and preference evolution in temporal forecasting.

Findings

RETE outperforms existing methods on benchmark datasets.

It effectively captures evolving user preferences.

Demonstrates robustness across multiple real-world datasets.

Abstract

With the increasing demands on e-commerce platforms, numerous user action history is emerging. Those enriched action records are vital to understand users' interests and intents. Recently, prior works for user behavior prediction mainly focus on the interactions with product-side information. However, the interactions with search queries, which usually act as a bridge between users and products, are still under investigated. In this paper, we explore a new problem named temporal event forecasting, a generalized user behavior prediction task in a unified query product evolutionary graph, to embrace both query and product recommendation in a temporal manner. To fulfill this setting, there involves two challenges: (1) the action data for most users is scarce; (2) user preferences are dynamically evolving and shifting over time. To tackle those issues, we propose a novel Retrieval-Enhanced Temporal Event (RETE) forecasting framework. Unlike existing methods that enhance user representations via roughly absorbing information from connected entities in the whole graph, RETE efficiently and dynamically retrieves relevant entities centrally on each user as high-quality subgraphs, preventing the noise propagation from the densely evolutionary graph structures that incorporate abundant search queries. And meanwhile, RETE autoregressively accumulates retrieval-enhanced user representations from each time step, to capture evolutionary patterns for joint query and product prediction. Empirically, extensive experiments on both the public benchmark and four real-world industrial datasets demonstrate the effectiveness of the proposed RETE method.