The Use of Big Data Analytics in Fraud Detection within Public Financial Management

Abstract

Fraud in public financial management poses a persistent
threat to fiscal integrity and public trust, particularly as
financial transactions become increasingly complex and
data-driven. This study examines how big data analytics can
be utilized to strengthen fraud detection processes in the
public sector. Using a systematic literature review approach,
the article synthesizes recent empirical and conceptual
research to evaluate the effectiveness, opportunities, and
challenges of implementing big data technologies. The
analysis reveals that advanced analytics significantly
improve the detection of anomalies and suspicious patterns
by enabling real-time monitoring and predictive modeling.
The discussion integrates evidence from multiple
jurisdictions, comparing technological capabilities with
institutional readiness, and addressing barriers such as data
privacy, skills gaps, and interoperability issues. Findings
suggest that big data analytics, when embedded within
robust governance frameworks, can enhance transparency,
improve audit efficiency, and support proactive fraud
prevention strategies in public financial systems.