Researchgnnrecommender systemszalandopytorch geometric
Zalando Integrates GNN Into Homepage Recommendations
|
8.1
Zalando engineers describe integrating a Graph Neural Network into its homepage recommender to improve click-through rate prediction. They train a GraphSAGE model with PyTorch Geometric on user-content interaction graphs to produce user and content embeddings, then add those embeddings as daily-updated features to the existing tabular production model to avoid full graph inference and mitigate cold-starts.
Scoring Rationale
Practical production-focused GNN integration guidance and empirical evaluation + limited novelty beyond established graph recommender techniques and architectures.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
