... in accuracy, precision and practical applicability for fraud detection. Design/methodology/approach The research analyzes a dataset of 48,746 firm-year observations, including 6,790 instances of fraud. Employing nine ML models (e.g. Random Forest, RUSBoost and LightGBM) and traditional logistic regression...

... auditors' ability to discover fraud in practice which could help policymakers develop effective interventions. Additionally, it provides several recommendations which could aid policymakers and audit firms in designing effective audit reforms to resolve the fraud detection deficit. Originality/value...

... areas that neuroscientific perspectives can potentially improve: 1) theory, 2) trust, 3) trait and state skepticism, 4) deception/fraud detection, and 5) skeptical judgment and action. The paper concludes with a discussion of the critical question of whether integrating a neuroscientific perspective...