Tracing Uncertainty in Reverse Logistics: A Decision Support System for Zero Defect Remanufacturing Quality and Quantity Control

The growing emphasis on circular economy principles has highlighted the importance of efficient remanufacturing processes in reducing waste and maximizing resource utilization. However, uncertainties in reverse logistics—specifically related to the quality, quantity, and timing of returned products—pose significant challenges for achieving defect-free remanufacturing. This paper proposes a Decision Support System (DSS) based on decision tree machine learning models to address uncertainties in remanufacturing. The DSS analyses key variables such as return timing and product condition to optimize remanufacturing outcomes by incentivizing early returns and improving product quality and return predictability. Additionally, the system integrates Zero Defect Manufacturing (ZDM) principles by leveraging real-time data and predictive analytics to minimize defects in remanufactured products. The paper discusses the implications of this approach for managing reverse logistics uncertainties and outlines future research directions for refining and implementing the DSS in practical settings. By bridging predictive analytics with sustainable manufacturing practices, the proposed framework contributes to more efficient and resilient remanufacturing systems within the circular economy.