Designing Large-Scale Identity Resolution Systems for Telecommunications Using Distributed Graph and Probabilistic Models
Keywords:
Customer Segmentation, Distributed Graph Processing, Entity Resolution, Identity Governance, Probabilistic Matching, TelecommunicationsAbstract
Modern telecommunications platforms manage billions of customer records distributed across billing, device registration, service subscription, customer care, and digital interaction systems. These systems evolve independently over time, producing fragmented and inconsistent customer identity representations that create operational risks across fraud detection, billing integrity, regulatory compliance, and downstream analytics. Deterministic matching approaches are insufficient at telecommunications scale because data is inherently incomplete, continuously evolving, and subject to identifier inconsistencies introduced through account merges, device replacements, and system migrations. This article presents a scalable framework for large-scale identity resolution in telecommunications environments that integrates deterministic matching, probabilistic inference based on the Fellegi-Sunter model, and distributed graph architectures. The model represents customer identity as a graph G = (V, E) consisting of vertices representing identity entities and edges representing relationship signals between the identity entities such as behavioral similarities, device correlations and billing overlaps. Finally, a composite identity matching score is calculated to reflect the probability that two records in G correspond to the same identity entity. As a result, it achieves a 9.1 percent deduplication rate on over 527 million customer records and a 68 percent reduction in false-positive fraud associations using graph-guided identity clustering. In hybrid identity resolution, it achieves an F1 score of 93.1 percent. Identity governance frameworks, including role-based access control and federated authorization, are combined to ensure compliance with GDPR and CCPA regulations. The results demonstrate that combining these three matching paradigms produces materially superior accuracy, scalability, and operational safety compared to any single approach.Downloads
References
Ivan P. Fellegi and Alan B. Sunter, "A Theory for Record Linkage", Journal of the American Statistical Association, 1969. Available: https://www.tandfonline.com/doi/abs/10.1080/01621459.1969.10501049
Junwei Hu et al., "When GDD Meets GNN: A Knowledge-Driven Neural Connection for Effective Entity Resolution in Property Graphs", Information Systems, 2025. Available: https://www.sciencedirect.com/science/article/pii/S0306437925000365
Mohammad Heydari et al., "Distributed Record Linkage in Healthcare Data with Apache Spark", arXiv preprint arXiv:2404.07939, 2024. Available: https://arxiv.org/abs/2404.07939
Xinxin Hu et al., "GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection", IEEE Transactions on Big Data, 2024. Available: https://ieeexplore.ieee.org/abstract/document/10388428
Neil G. Marchant et al., "Bayesian Graphical Entity Resolution Using Exchangeable Random Partition Priors", Journal of Survey Statistics and Methodology, 2023. Available: https://academic.oup.com/jssam/article/11/3/569/6969687
Lasya Vyakaranam et al., "Simplifying Graph-Parallel Computation in Apache Spark with GraphX", 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA), IEEE, 2024. Available: https://ieeexplore.ieee.org/abstract/document/10800958
Xinxin Hu et al., "Mining Mobile Network Fraudsters with Augmented Graph Neural Networks", Entropy, 2023. Available: https://www.mdpi.com/1099-4300/25/1/150
Thanh Huan Vo et al., "Extending the Fellegi-Sunter Record Linkage Model for Mixed-Type Data with Application to the French National Health Data System", Computational Statistics and Data Analysis, 2023. Available: https://www.sciencedirect.com/science/article/abs/pii/S0167947322002365
Lavanya Elluri et al., "An Integrated Knowledge Graph to Automate GDPR and PCI DSS Compliance", 2018 IEEE International Conference on Big Data (Big Data), IEEE, 2018. Available: https://ieeexplore.ieee.org/abstract/document/8622236
Alexandros Karakasidis and Georgia Koloniari, "Efficient Privacy Preserving Record Linkage at Scale Using Apache Spark", 2022 IEEE International Conference on Big Data (Big Data), IEEE, 2022. Available: https://ieeexplore.ieee.org/abstract/document/10020832
Reynold S. Xin et al., "GraphX: A Resilient Distributed Graph System on Spark", First International Workshop on Graph Data Management Experiences and Systems (GRADES), ACM, 2013. Available: https://dl.acm.org/doi/abs/10.1145/2484425.2484427
An Tong et al., "GDFGAT: Graph Attention Network Based on Feature Difference Weight Assignment for Telecom Fraud Detection", PLOS ONE, 2025. Available: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0322004
Olivier Binette and Rebecca C. Steorts, "(Almost) All of Entity Resolution", Science Advances, 2022. Available: https://www.science.org/doi/full/10.1126/sciadv.abi8021
Junhang Wu et al., "Beyond the Individual: An Improved Telecom Fraud Detection Approach Based on Latent Synergy Graph Learning", Neural Networks, 2024. Available: https://www.sciencedirect.com/science/article/abs/pii/S0893608023005737
Yuhang Zhang et al., "Scalable Entity Resolution Using Probabilistic Signatures on Parallel Databases", Proceedings of the 27th ACM International Conference on Information and Knowledge Management, ACM, 2018. Available: https://dl.acm.org/doi/abs/10.1145/3269206.3272016
George Papadakis et al., "Three-Dimensional Entity Resolution with JedAI", Information Systems, 2020. Available: https://www.sciencedirect.com/science/article/abs/pii/S0306437920300570
Robert A. Barton et al., "Graph Neural Networks for Inconsistent Cluster Detection in Incremental Entity Resolution", arXiv preprint arXiv:2105.05957, 2021. Available: https://arxiv.org/abs/2105.05957
Olalekan Hamed Olayinka, "Data Driven Customer Segmentation and Personalization Strategies in Modern Business Intelligence Frameworks", World Journal of Advanced Research and Reviews, 2021. Available: https://doi.org/10.30574/wjarr.2021.12.3.0658
Amir Ghasemian et al., "Evaluating Overfit and Underfit in Models of Network Community Structure", IEEE Transactions on Knowledge and Data Engineering, 2019. Available: https://ieeexplore.ieee.org/abstract/document/8692626
George Papadakis et al., "A Critical Re-Evaluation of Record Linkage Benchmarks for Learning-Based Matching Algorithms", 2024 IEEE 40th International Conference on Data Engineering (ICDE), IEEE, 2024. Available: https://ieeexplore.ieee.org/abstract/document/10598022
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
