A Machine Learning Approach for Predicting and Mitigating Pallet Collapse during Transport: The Case of the Glass Industry

Abstract

This study explores the prediction and mitigation of pallet collapse during transportation within the glass packaging industry, employing a machine learning approach to reduce cargo loss and enhance logistics efficiency. Using the CRoss-Industry Standard Process for Data Mining (CRISP-DM) framework, data were systematically collected from a leading glass manufacturer and analysed. A comparative analysis between the Decision Tree and Random Forest machine learning algorithms, evaluated using performance metrics such as F1-score, revealed that the latter is more effective at predicting pallet collapse. This study is pioneering in identifying new critical predictive variables, particularly geometry-related and temperature-related features, which significantly influence the stability of pallets. Based on these findings, several strategies to prevent pallet collapse are proposed, including optimizing pallet stacking patterns, enhancing packaging materials, implementing temperature control measures, and developing more robust handling protocols. These insights demonstrate the utility of machine learning in generating actionable recommendations to optimize supply chain operations and offer a foundation for further academic and practical advancements in cargo handling within the glass industry.