Graph-Based Customer Segmentation with GraphSAGE on a Customer–Vehicle Bipartite Network
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
Sezdi, A., Bilgin, M. (2025). Graph-Based Customer Segmentation with GraphSAGE on a Customer–Vehicle Bipartite Network. *Orclever Proceedings of Research and Development*, 7(1), 16-29. https://doi.org/10.56038/oprd.v7i1.670
Bibliographic Info
More from Orclever Proceedings of Research and Development
Single-Bath Dyeing of Blends of Cotton Fibers with New Generation Polyacrylonitrile Fibers with Reactive Dye in Line with the Target of Sustainable Production
Yıldıray Fatih Dilsiz, Seda Keskin, Rıza Atav
2025 · Vol 7 · Issue 1
The Green Step Upper: A Novel Sustainable Bonding Method Replacing Solvent-Based Adhesives in Footwear Upper Assembly
Baris Bekiroglu, Mustafa Yener
2025 · Vol 7 · Issue 1
Innovative Technological Strategies to Enhance Bioavailability in Germinated Grains
Ebru Bozkurt Abdik
2025 · Vol 7 · Issue 1
Natural Language Processing-Based Layered Reconciliation System for Financial Transaction Analysis
Dilara Hazırlar, Özlem Avcı, Mesut Tekir
2025 · Vol 7 · Issue 1
An Integrated Deep Learning Framework for Automated Quality Control and Process Optimization in Slasher Indigo Dyeing
Mohammad Muttaqi, Gizem Daskaya, Kerem Cakir
2025 · Vol 7 · Issue 1
Development of a Secure Structural Component to Mitigate Environmental Contamination at Ports During the Transfer of Granular Materials in Global Maritime Logistics: Ecological Port Loading Bunker
Özge Güler, M.Cemal Çakır
2025 · Vol 7 · Issue 1