Forensic Analytics for Detecting Subtle Procurement Irregularities

Michael A. Turner

Forensic Analytics for Detecting Subtle Procurement Irregularities

Author(s)	Prof. Dr. Michael A. Turner
Country	United States
Abstract	Procurement irregularities do not always appear as conspicuous fraudulent transactions. Contemporary purchasing environments generate large volumes of purchase orders, supplier records, invoice entries, approval events, tender documents, and payment transactions in which problematic behavior may be distributed across numerous individually plausible activities. Conventional rule-based auditing can therefore overlook low-intensity irregularities such as repeated purchases immediately below approval thresholds, gradual vendor concentration, minor invoice deviations, unusual approval sequences, repetitive awards, and coordinated timing patterns. This study develops a layered forensic analytics framework for identifying such subtle procurement irregularities while preserving interpretability for auditors and compliance professionals. Because no verified organizational dataset was supplied for the present study, the empirical component is explicitly designed as a simulation-based methodological evaluation rather than a representation of completed field research. A synthetic procurement environment of 1,200 transaction profiles is conceptualized around monetary, vendor, temporal, procedural, and relational risk attributes. Four analytical layers are evaluated: conventional red-flag screening, digit- and threshold-based forensic tests, unsupervised anomaly detection, and an integrated forensic risk ensemble. The proposed framework combines normalized indicators through a transaction-level risk score that prioritizes cases showing several weak but mutually reinforcing deviations. Simulated evaluation indicates that the integrated approach can provide stronger discriminatory performance than isolated controls, principally because subtle irregularities become more visible when transactional deviations, vendor behavior, process exceptions, and temporal signals are considered jointly. The study contributes an interpretable framework that positions forensic analytics as a risk-prioritization mechanism rather than an automated accusation system. The resulting approach can support continuous auditing, procurement governance, targeted investigation, and more proportionate allocation of audit resources while retaining human professional judgment as the final decision mechanism.
Keywords	forensic analytics, procurement irregularities, anomaly detection, continuous auditing, procurement fraud risk, red-flag analytics, vendor risk
Field	Engineering
Published In	Volume 6, Issue 2, March-April 2025
Published On	2025-04-02

View / Download PDF File

About AJAMIR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+1-872-302-3851	editor@ajamir.com

American Journal of Advanced Multidisciplinary Innovation and Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Forensic Analytics for Detecting Subtle Procurement Irregularities

Share this