# Returnformer: A Graph Transformer-Based Model for Predicting Product Returns in E-Commerce

## TL;DR

This paper introduces Returnformer, a new model that uses graph transformers to predict product returns in e-commerce, helping retailers reduce losses.

## Contribution

The Returnformer model integrates global topological embeddings and a graph-level attention mechanism for improved return prediction.

## Key findings

- Returnformer outperforms four machine learning models in prediction accuracy.
- The model captures user–product dependencies using bipartite graph structures.
- It enables proactive return risk identification before payment.

## Abstract

E-commerce retailers bear substantial additional costs arising from high product return rates due to lenient return policies and consumers’ impulsive purchasing. This study aims to accurately predict product return behavior before payment, supporting proactive return management and reducing potential losses. Based on the Graph Transformer, we proposed a novel return prediction model, Returnformer, which focuses on capturing user–product connections represented in topological structures of bipartite graphs. The Returnformer first integrates global topological embeddings into original node features to alleviate structural information loss caused by graph partitioning. It then employs a Graph Transformer to capture long-range user–item dependencies within local subgraphs. In addition, a graph-level attention mechanism is introduced to facilitate the propagation of global return patterns across different subgraphs. Experiments on a real-world e-commerce dataset show that the Returnformer outperforms four machine learning models in terms of prediction accuracy, demonstrating superior performance compared to the state-of-the-art models. The proposed model enables retailers to identify potential return risks prior to payment, thereby supporting timely and proactive preventive interventions.