EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Approach Using Embeddings and Community Detection for User Number Portability Prediction in the Telecommunications Sector

Ricardo Maguiña, Rodrigo Pozo, Daniel Mori

Computers · 19.11.2026 · 15 (11) · 856

DOI: 10.3390/computers15110856 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 19.11.2026. Verfasst von Ricardo Maguiña und 2 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Peruvian University of Applied Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Peruvian University of Applied Sciences

Zitieren

APA

Maguiña, R., Pozo, R., & Mori, D. (2026). Hybrid Approach Using Embeddings and Community Detection for User Number Portability Prediction in the Telecommunications Sector. Computers, 15(11), 856. https://doi.org/10.3390/computers15110856

Vancouver

Maguiña R, Pozo R, Mori D. Hybrid Approach Using Embeddings and Community Detection for User Number Portability Prediction in the Telecommunications Sector. Computers. 2026;15(11):856. doi:10.3390/computers15110856

BibTeX
@article{Maguia2026,
  author = {Maguiña, Ricardo and Pozo, Rodrigo and Mori, Daniel},
  title = {Hybrid Approach Using Embeddings and Community Detection for User Number Portability Prediction in the Telecommunications Sector},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {856},
  doi = {10.3390/computers15110856}
}
Kostenlos starten →