A graph-based approach using GraphSAGE effectively learns customer and vehicle embeddings for segmentation and recommendation tasks.
Researchers modeled customer-vehicle interactions as a bipartite graph and used GraphSAGE to learn inductive node representations. These representations were then used to construct customer segments via K-Means clustering. The results showed that the learned embeddings provided a practical and scalable foundation for recommendation and customer understanding tasks.
Abstract
This study models customer–vehicle interactions in an online used-car platform as a bipartite structure, constructing a graph with customer (U) and vehicle (V) nodes. Relations between the two node sets are defined only by edges representing realized purchase events (e=(u,v,t)), thereby focusing on a signal with high business value and relatively low noise. On this graph, inductive node representations (embeddings) are learned with GraphSAGE. During training, link prediction is used solely as a self-supervised proxy task; optimization employs an MLP-based scorer with Binary Cross-Entropy (BCE) loss. Early stopping is triggered when the BCE on a temporally held-out validation set stops improving; together with temporal negative sampling, this prevents leakage of future information.
The objective is to obtain high-quality customer/vehicle embeddings. The learned representations are then used to construct embedding-based customer segments via K-Means. Segmentation quality is evaluated using the Silhouette and Calinski–Harabasz scores. The results show that GraphSAGE embeddings learned on the purchase-induced bipartite graph provide a practical and scalable foundation for recommendation/targeting and customer understanding tasks
References
- 1.S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, “Bpr: Bayesian personalized ranking from implicit feedback,” in UAI, 2009.
- 2.A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in KDD, 2016.
- 3.W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in NeurIPS, 2017.
- 4.R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec, “Graph convolutional neural networks for web-scale recommender systems,” in KDD, 2018.
- 5.X. Wang, X. He, M. Wang, F. Feng, and T.-S. Chua, “Neural graph collaborative filtering,” in SIGIR, 2019.
- 6.X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, “Lightgcn: Simplifying and powering graph convolution network for recommendation,” in SIGIR, 2020.
- 7.Z. Wu et al., “A comprehensive survey on graph contrastive learning,” IEEE TPAMI, 2021, arXiv:2106.05264.
- 8.Y. You, T. Chen, Y. Sui, T. Chen, Z. Wang, and Y. Shen, “Graph contrastive learning with augmentations,” in NeurIPS, 2020.
- 9.P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” Journal of Computational and Applied Mathematics, vol. 20, pp. 53–65, 1987.
- 10.T. Calinski and J. Harabasz, “A dendrite method for cluster analysis,” Communications in Statistics, vol. 3, no. 1, pp. 1–27