NUMERICAL METHODS AND ARTIFICIAL INTELLIGENCE: SOLVING COMPLEX MATHEMATICAL PROBLEMS THROUGH DATA-DRIVEN ALGORITHMS

Abstract

This study examined the impact of artificial intelligence (AI) on forecasting accuracy, recovery efficiency, and recycling performance in cloud-enabled closed-loop supply chains. A quantitative research design was applied, and data was collected from a sample of 320 supply chain professionals across manufacturing, retail, and e-commerce sectors. Structural Equation Modeling (SEM) was used to analyze the relationships between AI, cloud integration, and supply chain performance variables. The results indicated that AI significantly improved forecasting accuracy (β = 0.44, p < 0.001), recovery efficiency (β = 0.39, p < 0.001), and recycling efficiency (β = 0.42, p < 0.001). Cloud integration also showed a positive effect on recycling efficiency (β = 0.36, p < 0.001), highlighting its role in facilitating real-time data sharing and coordination. Descriptive statistics revealed high mean values for all variables, ranging from 3.97 to 4.22, indicating strong agreement among respondents regarding the effectiveness of AI and cloud technologies. The findings demonstrated that AI-driven systems enhanced operational efficiency, reduced uncertainty, and supported sustainable practices by optimizing resource utilization and improving reverse logistics processes. This study contributed to the literature by providing empirical evidence on the integration of AI and cloud computing in closed-loop supply chains and offered practical insights for organizations seeking to adopt intelligent and sustainable supply chain solutions.

Keywords : Artificial Intelligence, Cloud Computing, Closed-Loop Supply Chain, Forecasting Accuracy, Recovery Efficiency, Recycling Efficiency