This article presents an artificial intelligence approach to predict supply chain performance, emphasizing its implications for sustainability. The study identifies 21 key performance indicators (KPIs) using the balanced scorecard (BSC) methodology as a performance measurement framework. While traditional grey first-order one-variable GM(1,1) models have been used for supply chain performance prediction, this study introduces a GM(1,1)-based artificial neural network (ANN) model to enhance prediction accuracy. The proposed approach evaluates performance based on the mean relative error (MRE), achieving significant reductions in MRE levels across various KPIs, from 77.09% to 0.23%. The grey neural network (GNN) model demonstrates superior predictive accuracy compared to the GM(1,1) model. The findings highlight the potential of the proposed AI approach in supporting informed decision-making by industrial managers, thereby promoting economic sustainability across all operational levels. The study combines grey system theory (GST) and ANNs to address the challenges of limited and uncertain data in supply chain performance prediction. The proposed GNN model integrates GM(1,1) with ANNs to effectively capture data non-linearity and improve prediction accuracy. The methodology involves data preprocessing, sequence operators, and the construction of a grey differential equation. The model is validated through case studies with three Bangladeshi apparel-manufacturing companies, demonstrating its effectiveness in predicting supply chain performance. The results show that the GNN model outperforms traditional models in terms of accuracy and reliability, providing a robust solution for supply chain performance prediction in uncertain environments.This article presents an artificial intelligence approach to predict supply chain performance, emphasizing its implications for sustainability. The study identifies 21 key performance indicators (KPIs) using the balanced scorecard (BSC) methodology as a performance measurement framework. While traditional grey first-order one-variable GM(1,1) models have been used for supply chain performance prediction, this study introduces a GM(1,1)-based artificial neural network (ANN) model to enhance prediction accuracy. The proposed approach evaluates performance based on the mean relative error (MRE), achieving significant reductions in MRE levels across various KPIs, from 77.09% to 0.23%. The grey neural network (GNN) model demonstrates superior predictive accuracy compared to the GM(1,1) model. The findings highlight the potential of the proposed AI approach in supporting informed decision-making by industrial managers, thereby promoting economic sustainability across all operational levels. The study combines grey system theory (GST) and ANNs to address the challenges of limited and uncertain data in supply chain performance prediction. The proposed GNN model integrates GM(1,1) with ANNs to effectively capture data non-linearity and improve prediction accuracy. The methodology involves data preprocessing, sequence operators, and the construction of a grey differential equation. The model is validated through case studies with three Bangladeshi apparel-manufacturing companies, demonstrating its effectiveness in predicting supply chain performance. The results show that the GNN model outperforms traditional models in terms of accuracy and reliability, providing a robust solution for supply chain performance prediction in uncertain environments.