GNN-GMVO: Graph Neural Networks for Optimizing Gross Merchandise Value in Similar Item Recommendation
This addresses the need for revenue optimization in e-commerce recommendation systems, though it is incremental as it adapts existing GNN methods to a specific business metric.
The paper tackles the problem of similar item recommendation in e-commerce by proposing a new Graph Neural Network architecture, GNN-GMVO, that directly optimizes Gross Merchandise Value (GMV) and includes a customized edge construction method; it shows higher prediction performance and expected GMV compared to state-of-the-art benchmarks on three real-world datasets.
Similar item recommendation is a critical task in the e-Commerce industry, which helps customers explore similar and relevant alternatives based on their interested products. Despite the traditional machine learning models, Graph Neural Networks (GNNs), by design, can understand complex relations like similarity between products. However, in contrast to their wide usage in retrieval tasks and their focus on optimizing the relevance, the current GNN architectures are not tailored toward maximizing revenue-related objectives such as Gross Merchandise Value (GMV), which is one of the major business metrics for e-Commerce companies. In addition, defining accurate edge relations in GNNs is non-trivial in large-scale e-Commerce systems, due to the heterogeneity nature of the item-item relationships. This work aims to address these issues by designing a new GNN architecture called GNN-GMVO (Graph Neural Network - Gross Merchandise Value Optimizer). This model directly optimizes GMV while considering the complex relations between items. In addition, we propose a customized edge construction method to tailor the model toward similar item recommendation task and alleviate the noisy and complex item-item relations. In our comprehensive experiments on three real-world datasets, we show higher prediction performance and expected GMV for top ranked items recommended by our model when compared with selected state-of-the-art benchmark models.