Supply Chain Sustainability Assessment System Based on Supervised Machine Learning Techniques: The Case for Sugarcane Agroindustry

Abstract

Addressing all aspects of sustainability with a single assessment method is challenging. Machine learning techniques for assessing the sustainability of the supply chain in sugar cane agroindustry are discussed in this paper. Sugar cane agroindustry involves a complex supply chain from upstream to downstream consisted of multi-stakeholders with different goals. A system of supply chain sustainability assessment based on supervised machine learning techniques, namely Artificial Neural Network (ANN) and Decision Tree was designed to assess the sustainability of the supply chain concerning three indicators, (economic, societal, and environmental indicators). The application of the system showed that ANN can be applied to predict the values of the three sustainability dimensions based on sustainability indicators and produce rational results with small errors. The prediction results of the sustainability dimension using ANN are used to determine the level of sustainability using the decision tree classification model. The classification accuracy obtained is 86%.