Sustainable sugarcane supply chain performance assessment: A review and research agenda

Abstract Supply chain sustainability has become a popular concept used by several businesses to increase business competitiveness. However, there is no standard for measuring supply chain sustainability and business competitiveness. The objectives of this research were to analyze and criticize existing methods for supply chain sustainability assessment and develop a new framework for future research. This study reviewed 151 scientific articles related to supply chain sustainability assessments from 2004 to 2020. The results show that many techniques are used for sustainability assessments. However, no single technique can comprehensively measure supply chain sustainability. Therefore, a new robust technique that accommodates complex data in a sustainable supply chain is required. The technique to be developed is a machine learning technique because it can accommodate multi-criteria problems with various nonlinear relationships. This research is a case study of the sugarcane agroindustry supply chain. The supply chain of the sugarcane agroindustry faces various sustainability issues caused by negative environmental impacts. The analysis results show that using machine learning techniques to assess sustainability for the sugarcane agroindustry’s supply chain has great potential to be developed. Machine learning applications for this assessment can also be used to monitor the performance of organizations. Thereby organizations can enhance their sustainability performance through data-driven decision-making.