<![CDATA[The aircraft spare parts supply chain is highly complex and vulnerable to delivery delays that may trigger Aircraft on Ground (AOG) conditions and increase operational costs. This study aims to analyze the characteristics of the aircraft spare parts supply network and to model delivery delay patterns in the repair process using a data-driven machine learning approach. The dataset consists of 4,962 shipment records with variables including delivery status (on-time/delay), ship vendor, origin point, destination point, lead time, and lead time category. Three classification algorithms, namely Decision Tree, Random Forest, and Logistic Regression, are applied to build and compare delay prediction models. The research stages comprise data preprocessing, splitting data into training and testing sets, model development, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results indicate that operational variables in the supply chain significantly influence delivery status and that the Random Forest model provides the best performance in capturing complex and non-linear delay patterns. These findings offer a basis for developing predictive decision support systems to mitigate delivery risks and enhance the reliability of Maintenance, Repair, and Overhaul (MRO) processes in the aviation industry.]]>
Copyrights © 2026
