Evaluating the performance of the raw material providers based on the customer-based LARG(CLARG) paradigm : a machine learning-based method

One of the critically important tasks of supply chain managers is to evaluate the performance of the raw material providers, especially in today’s modern and dynamic business environment. In this regard, the current study focuses on the evaluation process of the raw material providers based on some crucial metrics named the customer-based LARG paradigm. For this purpose, based on a real-world case study in the agri-food industry, the main criteria and sub-criteria are determined. Afterward, to evaluate the performance of the potential raw material providers, a machine learning-based method by combining the stochastic best-worst method and weighted decision tree is developed. In general, this research contributes to the literature by proposing an efficient machine learning-based model to investigate the raw material provider selection problem for the agri-food industry based on the customer-based LARG paradigm. The results obtained from the implementation of the developed approach show that the general, leagility, resilience, customer-based, and green criteria are the most significant ones, respectively. Also, among the sub-criteria, “Service level”, “Robustness”, “Cost”, “Quality”, “Manufacturing flexibility”, “Delivery speed”, “Waste management”, and “Restorative Capacity” are specified as the best ones. Additionally, based on the achieved outcomes, the effectiveness, reliability, and validity of the proposed machine learning-based approach are confirmed.