Hybrid Approach Using Embeddings and Community Detection for User Number Portability Prediction in the Telecommunications Sector
We evaluate a hybrid framework for predicting next-month mobile number port-out using operational subscriber features, Word2Vec representations of service interactions, and Louvain community descriptors within XGBoost. A chronological protocol separates training (January–July 2025), probability calibration (August), threshold validation (September), and independent testing (October–November). The held-out cohort comprises 8,112,036 line-month records with 150,202 portability events (1.85%). Six models are compared under the same population and target. The full hybrid attains ROC-AUC 0.7266, PR-AUC 0.05215 and Brier score 0.017912, versus 0.7277, 0.05100 and 0.017922 for tabular XGBoost. XGBoost with Word2Vec leads PR-AUC (0.05298), whereas random forest leads ROC-AUC (0.7385). Class-weight analysis (1, 4 and 8) reveals a trade-off between recall and global discrimination. A frozen training-period graph contains 6704 small, highly fragmented communities, helping explain limited incremental graph value. We additionally report calibration, complete threshold-specific confusion matrices, provenance checks and a functional risk-analysis dashboard. The evidence supports representation-specific gains, not uniform superiority of combining all three methods.
Authors
- Ricardo Maguiña
- Rodrigo Pozo
- Daniel Mori
Institutions
- Peruvian University of Applied Sciences (PE)
Publication Details
- Journal
- Computers
- Published
- 2026-11-19
- DOI
- https://doi.org/10.3390/computers15110856
- Primary Topic
- Customer churn and segmentation
- Type
- article
- Field-Weighted Citation Impact
- 0.00