Integrating Artificial Intelligence and Predictive Analytics in Supply Chain Management to Minimize Carbon Footprint and Enhance Business Growth in the USA

Abstract

The research investigates the role of artificial intelligence and predictive analytics in integrating the practices of supply chain management for the growth of a business in a sustainable manner. A predictive model on the emission factors was then developed using a Random Forest algorithm from machine learning techniques against the historical data from the US Environmental Protection Agency on "Supply Chain Greenhouse Gas Emission Factors for USUS Industries and Commodities." It yielded an average Mean Squared Error of 0.00141 with an R-squared value of 0.9858, explaining almost 99% of the variance in actual emission factors across various industries. The research results show the potential of AI-driven insights in spotting high-emission areas, facilitating targeted interventions, and thus supporting data-driven decision-making in SCM. Case studies drawn from industries such as electronic manufacturing and food processing show the practical application of this model by showing how businesses can reduce their carbon footprints while enhancing operational efficiency and market competitiveness. The study also addresses the pitfalls that may characterize model implementation, such as poor data quality, complex models, and continuous updating. It makes business recommendations to adopt similar strategies, emphasizing cross-functional expertise, stakeholder buy-in, and ethical considerations. It deepens a growing literature on sustainable supply chain management and establishes a framework through which firms can harness AI and predictive analytics to pursue environmental and economic objectives.