Supply Chain 4.0: A Machine Learning-Based Bayesian-Optimized LightGBM Model for Predicting Supply Chain Risk

Abstract

In today’s intricate and dynamic world, Supply Chain Management (SCM) is encountering escalating difficulties in relation to aspects such as disruptions, globalisation and complexity, and demand volatility. Consequently, companies are turning to data-driven technologies such as machine learning to overcome these challenges. Traditional approaches to SCM lack the ability to predict risks accurately due to their computational complexity. In the present research, a hybrid Bayesian-optimized Light Gradient-Boosting Machine (LightGBM) model, which accurately forecasts backorder risk within SCM, has been developed. The methodology employed encompasses the creation of a mathematical classification model and utilises diverse machine learning algorithms to predict the risks associated with backorders in a supply chain. The proposed LightGBM model outperforms other methods and offers computational efficiency, making it a valuable tool for risk prediction in supply chain management.

Keywords

• machine learning
• supply chain management
• backorder risk
• prediction
• resilience
• light gradient boosting machine