Is this project an undergraduate, graduate, or faculty project?
Undergraduate
Project Type
individual
Campus
Worldwide
Authors' Class Standing
Dean Sutherland, Senior
Lead Presenter's Name
Dean Sutherland
Lead Presenter's College
DB College of Business
Faculty Mentor Name
Burak Cankaya
Abstract
This study aims to analyze aircraft incident data from the Federal Aviation Administration (FAA) between 1978 and to current for the top five largest airlines in the United States. The goal is to predict conditions that have a higher chance of causing injury and to determine the best machine-learning model for this prediction. The target variable of "injuries occurred" is processed through Machine Learning methods such as Deep Learning, Logistic Regression, and Support Vector Machine. While analyzing and understanding the incidents, the text mining methodology is used in real-world incident remarks reports. The main scope of the study is not only to predict the injuries but also to understand and explain the complex fault mechanism that creates these incidents and recommend actions for these airlines to reduce the number and severity of these incidents by combining inferences between variables with Subject Matter Expertise in the area. This study provides insights into improving safety in the aviation industry, commonalities of injuries, and how it contributes to the literature by predicting injuries in legacy airlines, explaining the patterns that create incidents, and creating prescriptions to reduce injuries that happen on airlines by using explainable Machine Learning models.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
Yes, Spark Grant
Understanding the Incidents on Legacy Airlines with Machine Learning: Case Study Top 5 US Airlines
This study aims to analyze aircraft incident data from the Federal Aviation Administration (FAA) between 1978 and to current for the top five largest airlines in the United States. The goal is to predict conditions that have a higher chance of causing injury and to determine the best machine-learning model for this prediction. The target variable of "injuries occurred" is processed through Machine Learning methods such as Deep Learning, Logistic Regression, and Support Vector Machine. While analyzing and understanding the incidents, the text mining methodology is used in real-world incident remarks reports. The main scope of the study is not only to predict the injuries but also to understand and explain the complex fault mechanism that creates these incidents and recommend actions for these airlines to reduce the number and severity of these incidents by combining inferences between variables with Subject Matter Expertise in the area. This study provides insights into improving safety in the aviation industry, commonalities of injuries, and how it contributes to the literature by predicting injuries in legacy airlines, explaining the patterns that create incidents, and creating prescriptions to reduce injuries that happen on airlines by using explainable Machine Learning models.