The success of supply chain businesses hinges on cost effectiveness and customer satisfaction metrics. Integrating financial, product, and information flows across SC levels is vital for long-term success and productivity. In the manufacturing facilities, estimating component costs is crucial for pricing discussions and cost management along the supply chain performance (SCP). Artificial neural network (ANN) is commonly employed for procurement price estimation due to its ability to handle vast data quickly and efficiently. This research presents a performance prediction model for Make-to-Order (MTO) supply chains based on the Supply Chain Operations Reference (SCOR®), incorporating multi-input and multi-put parameters. Utilizing real data from general manufacturing facilities located in Oman for repairing trucks engines and machines, the model employs ANN technique to estimate total serving cost and order satisfaction time. Developed in MATLAB 2022b, the model's network topologies were selected via cross-validation, showing strong positive correlations between predicted and projected performance values. The integrated model offers potential to enhance supply chain operations by mitigating unexpected changes or failures. Practical implications include increased estimation accuracy, optimized inventory and production planning, improved supplier and transportation management, risk mitigation, and personalized client experiences. Furthermore, the study aligns with the United Nations’ Sustainable Development Goal 9 by promoting digitalization, infrastructure development, and sustainable supply chain performance in manufacturing facilities.