Big Data Analytics and Explainable AI in Supply Chain Management

In the Supply Chain Management (SCM) field, complexity and high volume of data require advanced analytics-based optimal decision-making. This study explored the potential of big data analytics and explainable artificial intelligence in SCM. It was the first study to propose a model to predict optimal shipment details, such as ports and stock-keeping units to be used while shipping. This research-to-practice study fills the gap via managerial data analysis based on business logic. Since predictions should be easily understandable by stakeholders, XAI techniques were adopted in the proposed model to make predictions transparent and interpretable. Transparency increases trust in AI-driven decisions and supports informed decisions. The results indicate that shipment logistics are significantly optimized through the proposed model providing cost reductions as well as operational performance improvements. Also, actionability evidences were presented in this study for using big data analytics with XAI to improve justification of its use for subsequent studies in SCM which opens a productive research avenue for future studies in SCM. This paper shows explicitly how XAI with big data analytics can transform SCM by facilitating an easy understanding of complex AI models from a managerial perspective for both academicians and managers.