The increasing complexity of global manufacturing supply chains has intensified the demand for reliable supplier performance and reduced operational inefficiencies. Predictive analytics models, leveraging statistical techniques, machine learning algorithms, and real-time data integration, are emerging as transformative tools for improving supplier accuracy and minimizing rework in manufacturing environments. These models enable organizations to move beyond reactive quality control toward proactive performance management by anticipating supplier-related risks and inefficiencies before they materialize. Predictive analytics enhances supplier accuracy through demand forecasting, historical performance analysis, and anomaly detection. By aligning supplier capacity with production requirements and predicting delivery delays or defect probabilities, manufacturers can identify reliable partners and intervene early to address potential disruptions. Similarly, predictive modeling supports rework reduction by uncovering patterns of recurring defects, tracing root causes to specific materials or processes, and recommending preemptive quality improvements. This proactive approach minimizes costly rework, reduces downtime, and enhances overall product reliability. Applications across industries—including automotive, electronics, and pharmaceuticals—demonstrate measurable benefits, such as reduced recall risks, improved compliance, and strengthened supplier collaboration. The integration of predictive models within manufacturing quality systems further streamlines decision-making and fosters evidence-based supplier development programs. Despite these advantages, challenges persist, including data integration complexities, model interpretability, and organizational resistance to change. Looking forward, combining predictive analytics with digital twins, blockchain-enabled data transparency, and prescriptive optimization frameworks offers promising pathways for future advancements. Overall, predictive analytics models represent a critical enabler of manufacturing competitiveness, enhancing supply chain resilience, reducing operational costs, and improving customer satisfaction through higher-quality outputs. Manufacturers must therefore invest in robust data infrastructures, advanced modeling capabilities, and collaborative supplier ecosystems to fully harness the potential of predictive analytics in minimizing rework and ensuring supplier accuracy.
Akinlade et al. (Fri,) studied this question.