🤖 AI Summary
Escalating global supply chain complexity exacerbates queuing congestion, material shortages, and inflationary risks, necessitating intelligent risk control mechanisms. This paper proposes an end-to-end automated machine learning (AutoML) framework specifically designed for supply chain security. It holistically integrates data preprocessing, automated feature engineering, collaborative sampling and hyperparameter optimization, ensemble modeling (RF, XGBoost, LightGBM, and neural networks), and deployment-ready inference. We introduce the first AutoML pipeline explicitly tailored to multi-task risk control scenarios. Empirical evaluation demonstrates substantial performance gains: 88.0% accuracy in fraud detection, 93.4% in equipment failure prediction, and 89.3% in material stockout forecasting. Crucially, joint sampling and hyperparameter optimization achieves 100% detection accuracy on critical tasks—establishing a practical, high-reliability technical pathway for intelligent supply chain decision-making.
📝 Abstract
The increasing scale and complexity of global supply chains have led to new challenges spanning various fields, such as supply chain disruptions due to long waiting lines at the ports, material shortages, and inflation. Coupled with the size of supply chains and the availability of vast amounts of data, efforts towards tackling such challenges have led to an increasing interest in applying machine learning methods in many aspects of supply chains. Unlike other solutions, ML techniques, including Random Forest, XGBoost, LightGBM, and Neural Networks, make predictions and approximate optimal solutions faster. This paper presents an automated ML framework to enhance supply chain security by detecting fraudulent activities, predicting maintenance needs, and forecasting material backorders. Using datasets of varying sizes, results show that fraud detection achieves an 88% accuracy rate using sampling methods, machine failure prediction reaches 93.4% accuracy, and material backorder prediction achieves 89.3% accuracy. Hyperparameter tuning significantly improved the performance of these models, with certain supervised techniques like XGBoost and LightGBM reaching up to 100% precision. This research contributes to supply chain security by streamlining data preprocessing, feature selection, model optimization, and inference deployment, addressing critical challenges and boosting operational efficiency.