University of Wisconsin Extended Campus is now Wisconsin Online Collaboratives! This name reflects the partnerships of the 13 universities within the Universities of Wisconsin–our state's premier system of public higher education. Through these partnerships we will continue to support online degrees, certificates and courses–along with support services to you.

Capstone Projects

Investigating Predictors of Aircraft on Ground Events and Their Variable Relationships

Program: Data Science Master's
Location: Minnesota (onsite)
Student: Kaitlyn Mahlen

Aircraft on Ground (AOG) is a widely used term within the aviation industry that indicates a problem with an aircraft or multiple aircraft. This problem is serious enough to prevent the aircraft from flying; hence, the aircraft is said to be “grounded” until the problem is fixed. An aircraft can be grounded for many different reasons; despite what the reason is, these events are almost always costly to the involved parties. A review of the literature found that AOG events can occur for many reasons, but there have not been many attempts to prevent them from occurring or to predict them happening. To initiate predictions of these events for a specific jet aircraft model, service case data was collected for this particular model including data related to the aircraft configuration, usage metrics, case metrics, and service bulletin information. Exploratory data analysis was completed to visualize relationships and statistics within the data; then, machine learning algorithms were applied to predict which class the case belonged to (0 = no AOG event and 1 = AOG event). Key findings include 18 statistically significant variables within the dataset, six variables that were strongly positively correlated with an AOG event, and 92.14% accuracy when using logistic regression to predict an AOG event. These findings can be utilized to inform the client organization and to prepare further analysis and machine learning models related to this topic.