Data mining approaches for aircraft accidents prediction: An empirical study on Turkey airline

Data mining approaches have been successfully applied in different fields. Risk and safety have always been important considerations in aviation. There is a large amount of knowledge and data accumulation in aviation industry. These data can be store in the form of pilot reports, maintenance reports, accident reports or delay reports. This paper applied the decision tree model on accident reports of the Federal Aviation Administration (FAA) Accident / incident Data System database, contains 468 accident data records for all categories of aviation between the years of 1970 to 2011. The decision tree classifier is use to predict the warning level of the component as the class attribute. We have explored the use of the decision tree technique on aviation components data. Decision Tree induction algorithm is applied to generate the model and the generated model is used to predict the warning of accidents in the airline database. This work may be useful for Aviation Company to make better prediction.