Procurement systems in emerging and high-regulation markets face increasing challenges due to the complexity of compliance requirements, operational opacity, and the heightened risk of fraud, collusion, and inefficiency. This review explores the evolution and impact of big data-enabled predictive compliance frameworks designed to address procurement risk in such environments. It examines how large-scale, heterogeneous data sources—ranging from contract records and transactional logs to external regulatory databases—can be integrated into intelligent monitoring systems capable of forecasting compliance breaches and procurement irregularities before they occur. The paper evaluates the technical underpinnings of these frameworks, including machine learning algorithms, anomaly detection models, rule-based engines, and real-time data pipelines. Additionally, it discusses governance structures, data quality challenges, and the role of regulatory interoperability in ensuring these systems are both effective and ethically sound. The study synthesizes insights from cross-sectoral implementations and offers recommendations for designing scalable, auditable, and context-aware compliance platforms for risk-resilient procurement in developing economies and tightly regulated sectors.
Aduloju et al. (Sun,) studied this question.