Construction and Application of AI-Based Intelligent Evaluation Model for DRP Level

Abstract

As a crucial component of enterprise supply chain management, Distribution Requirements Planning (DRP) directly impacts product distribution efficiency, inventory control levels, and customer responsiveness. Traditional DRP rating evaluation methods, which predominantly rely on expert experience and static analysis, exhibit issues such as excessive subjectivity and poor dynamic adaptability, making them inadequate for modern complex supply network demands. To address these challenges, this study proposes an AI-powered intelligent DRP rating evaluation model. By integrating machine learning algorithms with multidimensional data features, the model establishes an evaluation index system and achieves dynamic rating determination. Through training and testing on multiple real-world corporate datasets, the results demonstrate that this evaluation system outperforms traditional methods in accuracy, stability, and practicality. In practical applications, the study explores the model's specific value in inventory optimization, distribution node configuration, and supply chain collaboration, providing theoretical foundations and practical pathways for enterprises to implement intelligent supply management. This research aims to drive the evolution of DRP system evaluation from static, subjective approaches toward intelligent, real-time methods, thereby enhancing the responsiveness and resource allocation efficiency of overall supply chain systems.