Track: Defense and Aviation

Abstract

Machine learning has been successfully applied to different fields, including aviation industry. There is a large amount of knowledge and data accumulation in the aviation industry which divided into reactive and proactive method in Safety Risk Management concept. Nowadays, those groups of data are collected as safety data and are used to predictive approach where potential unsafe events and precursors are identified beforehand, and mitigation strategies are implemented to prevent incident/accident. This study aims to predict incident/accident events on aircraft in the MRO industry based on investigation event data so that mitigation can be carried out to reduce the impact of aircraft damage and even prevent more fatal things from occurring. From the prediction model built, it is hoped that the factors or variables that can determine the risk index category in an incident/accident event can also be identified. The processing data using several algorithms namely SVM, Naïve Bayes, Decision Tree, and Random Forest. The accuracy results are random forest (94.29%), decision tree (91.43%), naïve bayes (91.43%) and SVM (83%).