Community Trend Prediction on Heterogeneous Graph in E-commerce

TL;DR

This paper presents a novel framework for predicting community-specific attribute trends in e-commerce using dynamic heterogeneous graphs and neural networks, enabling better anticipation of fashion trends.

Contribution

It introduces a unified approach combining bipartite and hypergraph models with recurrent neural networks to forecast attribute trends within communities.

Findings

Outperforms existing methods on real-world e-commerce datasets.

Effectively captures the evolution of attribute tags over time.

Demonstrates ability to predict community trends in advance.

Abstract

In online shopping, ever-changing fashion trends make merchants need to prepare more differentiated products to meet the diversified demands, and e-commerce platforms need to capture the market trend with a prophetic vision. For the trend prediction, the attribute tags, as the essential description of items, can genuinely reflect the decision basis of consumers. However, few existing works explore the attribute trend in the specific community for e-commerce. In this paper, we focus on the community trend prediction on the item attribute and propose a unified framework that combines the dynamic evolution of two graph patterns to predict the attribute trend in a specific community. Specifically, we first design a communityattribute bipartite graph at each time step to learn the collaboration of different communities. Next, we transform the bipartite graph into a hypergraph to exploit the associations of different attribute tags in one community. Lastly, we introduce a dynamic evolution component based on the recurrent neural networks to capture the fashion trend of attribute tags. Extensive experiments on three real-world datasets in a large e-commerce platform show the superiority of the proposed approach over several strong alternatives and demonstrate the ability to discover the community trend in advance.