Machine learning models for fraud detection in telecommunication networks: A PRISMA – based review
📄
Abstract
Abstract: The high growth rate of the telecommunication networks in the last two decades has changed the world connections, digital transactions, and socio–economic interactions to great extent. The development of mobile users, internet services, and digital payments is making telecommunication infrastructure to be more important aspect of modern society. However, with the rapid digitalisation, advanced fraud schemes have also been able to target users and operators with ease. Telecommunication encompasses within its scope a wide range of organised crimes such as subscription fraud, SIM swap fraud, international revenue share fraud, Wangiri fraud etc causing significant loss to service providers. Conventional systems of detection based on rules are not sufficient to combat the emerging and dynamic fraud schemes and requires more data driven approaches. Machine - learning (ML) techniques have become a powerful method in identifying sophisticated fraud indicators in large scale telecommunication data comprising of call detail records (CDRs) and transactional logs. The models of supervised learning which include Logistic regression, support vector machine, Decision tree, and ensemble models like Random Forest algorithms and XG Boost have shown better results in detection. In the recent times, the deep learning methos has been employed to learn anomalies in telecom data. Although there has been a rise in the number of studies in this field, there is a lack of comparability across studies. This PRISMA – based systematic review evaluates the findings from few of the selected studies to assess the machine learning models, performance outcomes and
research gaps in telecom fraud detection.
🏷️
Keywords
📖
Full Article
🖼️
Figures & Tables
📚
References
⚖️
Ethics Declarations
Ethics Approval and Consent to Participate
Users can freely download, share, and reuse the article for any purpose (even commercially), as long as they give proper credit to the original author.
Competing Interests
Users can freely download and share the article, but they are strictly prohibited from using it or selling it for commercial profit.
Consent for Publication
Users can only read and view the article for personal use; they cannot copy, redistribute, or reuse any part of it without explicit permission from your journal.
📋
Editorial Lifecycle
Audit TrailComplete editorial process — cryptographically verified
Editorial Lifecycle
Audit TrailEditorial Process Audit Trail
NFSU-2026-V5-I1-J-2026-0113-CHAIN
✓ Verified · 0 blocks · Genesis 0x9f2bNo History Found
This manuscript has no status history yet.
🔐
Verification & Trust
CompliantCOPE · ICMJE · FAIR · ORCID · CLOCKSS
Verification & Trust
CompliantArticle Integrity Verified
All editorial chain blocks cryptographically verified · Compliant with COPE, ICMJE, and FAIR standards