Predictive Analytics and Machine Learning Applications in the USA for Sustainable Supply Chain Operations and Carbon Footprint Reduction

Abstract

With the escalating concerns worldwide regarding climate change and environmental sustainability, there is an increasing focus on emissions and ecological footprint reduction in supply chain operations in the USA. This study explored the application of predictive analytics and machine learning in the supply chain management domain for reducing carbon emissions and granting sustainable operations. For the present research paper, Walmart organization provided all the supply chain activity data used in this research study, it consisted of comprehensive data on their industrial activity levels, production outputs, energy consumption, types of fuels used, geographical data, and weather conditions. Three Machine learning algorithms were trained and tested, notably, Random Forest, XG-Boost, and the Bagging algorithm. Based on all the metrics, Random Forest was the best classifier because of its excellent generalization, high measure of precision and recall, and high AUC. As per the results, the random forest algorithm was the most accurate in its predictions of all the models evaluated.  Implementing the random forest benefits businesses in America with high accuracy and robustness, flexibility, scalability, risk management, and Mitigation. As regards the US economy, deploying the Random Forest can benefit the government in the following ways: reducing carbon footprint, attracting foreign investment, and enhancing competitive advantage.