Intelligent System For Enhancement Of Foreign Trade Depending On Sustainable Development Concepts

Trading and foreign ties of the economy are linked and dependent of each other as trading is best way to connect the nations. In this paper, we investigate the role of artificial intelligence (AI) and green innovation in achieving carbon neutrality, alongside an evaluation of machine learning algorithms for optimizing supply chain performance. AI\'s direct effect on carbon neutrality is found to be positive but insignificant; however, its interaction with the Paris Agreement significantly enhances carbon reduction efforts. Energy transitions also support carbon neutrality but can be negatively influenced by geopolitical risks. Foreign trades are popular is many sectors of industries such as energy sectors that is manifested in oil and gas, power and minerals. Green innovation emerges as a key driver for carbon neutrality, whereas financial development does not have a meaningful impact. To analyze supply chain optimization, we compared the performance of five machine learning algorithms: Random Forest, XGBoost, Logistic Regression, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The proposed algorithms are used to study and analyse the dataset and hence the metrics of performance are extracted. Using key metrics such as accuracy, precision, recall, F1-score, and AUC (Area Under the Curve). Random Forest outperformed the other algorithms, achieving a high accuracy of 92%, precision of 0.91, recall of 0.90, and an F1-score of 0.905. Its AUC value of 0.95 indicates excellent classification performance, making it highly effective for complex supply chain datasets. XGBoost closely followed, with an accuracy of 90% and an AUC of 0.93. These findings suggest that Random Forest is the most reliable algorithm for optimizing supply chain processes in big data contexts.