Answers are grounded in this paper and cite their sources.
Analysis demonstrates the role of predictive analytics in vendor reliability for supply chain management, suggesting improved procurement efficiency.
Effective Supply chain management (SCM) relies heavily on vendor reliability, as inconsistencies can cause disruptions, increase costs, and diminish customer satisfaction. Traditional assessment methods, which primarily depend on historical data, often fail to address dynamic market conditions and unforeseen disruptions. This study proposes a tailored Random Forest model to enhance predictive accuracy in vendor reliability assessment. The model integrates domain-specific criteria—including compliance thresholds, delivery benchmarks, quality ratings, and responsiveness metrics—to produce precise forecasts. Structured vendor performance data, comprising delivery timelines, quality ratings, compliance scores, and responsiveness metrics, were systematically processed. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, while rigorous preprocessing involving imputation, outlier handling, and normalization ensured data integrity. The Random Forest model achieved 92.50% classification accuracy, significantly outperforming traditional models. Precision, recall, and F1-score results confirmed balanced performance, reflecting a 35% improvement over conventional methods. Incorporating compliance scores further enhanced forecast reliability. Additionally, a "Vendor of the Year" system was validated, enabling objective identification and recognition of high-performing vendors. This research advances data-driven SCM by improving procurement efficiency, reducing inventory disruptions, and strengthening operational resilience, thereby providing a foundation for future real-time integration and broader industry applications.
No takes yet. Share an insight, caveat, or question.
Khalil et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: