A Graph Neural Network Approach for Product Relationship Prediction

TL;DR

This paper demonstrates how inductive graph neural networks, specifically GraphSAGE, can effectively predict product relationships in markets, outperforming traditional models and providing interpretability insights.

Contribution

It introduces an adjacency prediction model enabling relationship prediction without neighborhood data and applies GNNs to product networks for the first time.

Findings

Double the prediction accuracy compared to traditional models.

Effective prediction of product relationships with no neighborhood information.

Interpretability analysis reveals attribute impacts on predictions.

Abstract

Graph Neural Networks have revolutionized many machine learning tasks in recent years, ranging from drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges. These representations also capture product feature information such as price, brand, or engineering attributes. They are combined with a classification model for predicting the existence of the relationship between products. Using a case study of the Chinese car market, we find that our method yields double the prediction performance compared to an Exponential Random Graph Model-based method for predicting the co-consideration relationship between cars. While a vanilla GraphSAGE requires a partial network to make predictions, we introduce an `adjacency prediction model' to circumvent this limitation. This enables us to predict product relationships when no neighborhood information is known. Finally, we demonstrate how a permutation-based interpretability analysis can provide insights on how design attributes impact the predictions of relationships between products. This work provides a systematic method to predict the relationships between products in many different markets.