Data analytics and whistleblowing in detection: an academic perspective

Fraud remains a widespread threat with serious financial and reputational consequences, costing organisations an estimated 5% of annual revenue globally. Traditional rule-based detection methods are increasingly inadequate due to evolving fraud schemes and rapid digitalisation across sectors. As a result, data analytics and machine learning have become essential tools for identifying hidden patterns, predicting fraudulent activities, and enabling real-time interventions, with advanced techniques such as network and graph analysis enhancing detection of organised fraud. Effective fraud prevention, however, requires a holistic approach that combines technological solutions with human mechanisms like whistleblowing to strengthen organisational resilience.