International Journal of Scientific Research and Engineering Development

This study investigates how artificial intelligence (AI) and data-driven analytics enhance product end-of-life (EOL) prediction, reverse supply chain optimization, and circular economy adoption. Primary data were collected from supply chain professionals, logistics managers, facility operators, and sustainability officers across multiple industries during February–March 2025. Critical parameters influencing reverse supply chain decisions such as product age, failure rate, repair cost, material value, and expected resale value were analyzed using simple yet effective methods, including expert scoring, rulebased heuristics, correlation analysis, clustering, survival analysis, and lightweight predictive modelling (logistic regression and decision trees).
The study demonstrates that integrating AI-based prediction with scenario analysis, Monte Carlo simulations, and operational checklists significantly improves EOL classification accuracy, facilitates remanufacturing feasibility assessments, and optimizes reverse logistics allocation. Clustering and dashboards help standardize operational decision-making and track KPIs such as recovery yield, processing costs, and return rates. Results indicate that these approaches can enhance reverse supply chain efficiency by 30–35%, reduce waste misclassification by 25–30%, and increase financial returns from product recovery programs by 22–33% across diverse industrial sectors. The findings highlight that even without complex multivariate tools, a combination of AI, data-driven analysis, and low-code visual tools can enable organizations to implement circular economy strategies effectively, achieving both environmental sustainability and operational efficiency.