Logistics Supply Chain Network Risk Prediction Model Based on Intelligent Random Forest Model

This article's goal is to investigate, using an intelligent random forest model (RFM), the logistics supply chain's network risk control method. The logistics supply chain network, a vital component of the modern economy, faces numerous potential risks, and uncertainties. To ensure the stability and sustainability of the supply chain, an effective risk control plan is crucial. This article examines the logistics supply chain network's risk management practices and proposes a risk management approach based on intelligent RFM. Many logistics supply chain network data are gathered and compared with other widely used models in the experimental section, including the convolutional network model and the analytic hierarchy process model. The accuracy, recall, and area under curve (AUC) value of the intelligent RFM are determined to be better than those of other models by comparing the experimental data. In particular, the intelligent RFM raises accuracy and recall on average by 3.5% and 4.1%, respectively. The recall of the RFM is 89.3%, which is 3.7% and 7.2% higher than that of the convolutional network model and the analytic hierarchy process model, respectively, in various dataset recall studies. RFM's AUC value in the experiment with AUC is 0.87 and 0.91, respectively, which is 0.05 and 0.08 higher than those of other models. These statistics demonstrate the superior network risk prediction capabilities of intelligent RFM in the logistics supply chain. The purpose of the article is to provide and demonstrate the superiority of a logistics supply chain network risk control approach based on intelligent RFM. This tactic can assist logistics companies in effectively identifying and assessing potential risks.