DATA-DRIVEN GREEN PROFIT DESIGN: SUSTAINABLE REMANUFACTURING BASED ON CUSTOMER SEGMENTATION

Abstract

Increasing global environmental awareness and stricter regulations have prompted manufacturers to focus on effective product life cycle management. Remanufacturing has emerged as a viable strategy for recovering end-of-life products, offering both economic and environmental benefits. However, assessing the profitability and risks associated with entering the remanufacturing market remains a significant challenge due to high costs, market uncertainties, and time-intensive evaluation processes. This study proposes a Data-Driven Green Profit Design (D-GPD) model to facilitate efficient and data-driven decision-making for remanufacturing business opportunities. The model integrates advanced data analysis techniques, including topic modeling, sentiment analysis, predictive modeling, and interpretable machine learning, to extract critical parameter values from diverse datasets. These parameters include environmental impact values, customer preferences, and competitive market data, which are crucial for evaluating remanufacturing feasibility. The proposed model employs a numerical optimization approach to assess the financial viability of incorporating remanufactured products into a company’s portfolio. By conducting an exhaustive search across all possible customer segment combinations, the D-GPD model enables rapid and systematic market assessments, identifying the most profitable remanufacturing strategies. A case study on smartphone products is conducted to demonstrate the effectiveness of the proposed methodology. The results highlight how the D-GPD model can help manufacturers optimize product design decisions, forecast market demand for remanufactured products, and maximize both economic and environmental benefits. This approach provides a practical and scalable framework for companies seeking to explore and expand their remanufacturing business opportunities in a data-driven and cost-efficient manner.