EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Survey of Machine Learning Techniques for Payroll Security in ERP Tax Systems

Bose babu Ravula, Yudhveer Kandukuri, Sojy John, Naveen Shrivastava, Mahesh Marri

European Journal of Technology · 21.11.2026 · 10 (1) · 39-59

DOI: 10.47672/ejt.3035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Technology, online erschienen am 21.11.2026. Verfasst von Bose babu Ravula und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Enterprise Resource Planning (ERP) systems are widely used to integrate payroll and tax management functionalities; however, because payroll data is sensitive and tax regulations are complex, ERP systems are highly exposed to security, fraud, and compliance risks. The traditional rule-based security and audit controls within ERP payroll and tax modules do not always identify changing fraud patterns, internal abuse, and real-time compliance infractions, whereas machine learning (ML) techniques have proved effective in augmenting payroll security and tax compliance with data-driven, adaptive intelligence. This survey aims to review how ML supports payroll security in ERP tax systems. Materials and Methods: The survey examines the machine learning methods used for payroll security in ERP tax systems, such as supervised and unsupervised learning, deep learning (DL), anomaly detection, and user behavior analytics. It considers how these methods facilitate early fraud detection, ongoing compliance auditing, and enhanced audit preparedness in intricate ERP settings, and it discusses ERP payroll and tax system architecture, data preprocessing, privacy and governance, and integration.

Findings

The synthesis of recent studies and practical applications indicates that ML-based approaches improve detection accuracy, reduce false positives, and strengthen audit readiness, although data quality, model transparency, and privacy remain open challenges. Implications to Theory, Practice, and Policy: The survey recommends explainable, privacy-preserving ML models combined with rule-based controls, providing practitioners and policy analysts with useful insights for designing secure, intelligent, and compliant ERP-based payroll systems. Keywords: Enterprise Resource Planning (ERP), Payroll Security, Machine Learning (ML), ERP Tax, Security.

Zitieren

APA

Ravula, B. B., Kandukuri, Y., John, S., Shrivastava, N., & Marri, M. (2026). A Survey of Machine Learning Techniques for Payroll Security in ERP Tax Systems. European Journal of Technology, 10(1), 39-59. https://doi.org/10.47672/ejt.3035

Vancouver

Ravula BB, Kandukuri Y, John S, Shrivastava N, Marri M. A Survey of Machine Learning Techniques for Payroll Security in ERP Tax Systems. European Journal of Technology. 2026;10(1):39-59. doi:10.47672/ejt.3035

BibTeX
@article{Ravula2026,
  author = {Ravula, Bose babu and Kandukuri, Yudhveer and John, Sojy and Shrivastava, Naveen and Marri, Mahesh},
  title = {A Survey of Machine Learning Techniques for Payroll Security in ERP Tax Systems},
  journal = {European Journal of Technology},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {39--59},
  doi = {10.47672/ejt.3035}
}
Kostenlos starten →