Research Summaries

Back Employing Machine Learning to Predict Student Aviator Performance (Continuation)

Fiscal Year 2021
Division Research & Sponsored Programs
Department NPS Naval Research Program
Investigator(s) Kamel, Magdi N.
Sponsor Office of the Chief of Naval Operations (Navy)
Summary Machine learning analysis of student aviator training performance data offers novel and more accurate methodologies for performance assessment to include identifying students for attrition or remediation as well as optimal pipeline assignments. In a previous effort, we identified important predictors and developed prediction models of performance in primary, intermediate, and advanced training based on data from ASTB, IFS, and API training. In this proposal, we extend the effort to later stages of training by developing models to predict performance in intermediate, advanced training as well as FRS based on primary training. The goal of the analysis is to: 1) determine the set of metrics predictive of student performance for these stages of training; 2) reveal trends and patterns which may indicate where and when remedial action is needed; and.3) identify which aviation pipeline a student will be most successful. The methodology proposed for this research is based on the Cross-Industry Standard Process for Data Mining (CRISP-DM). The CRISP-DM process model includes six phases that address the main issues in data mining. The six phases are undertaken in a cyclical and iterative manner and include: Business/Mission Understanding, Data Understanding, Data Preparation, Modeling, Evaluation and Deployment. The research deliverables include a technical report detailing the application of the methodology to the identified stages of aviation training, a PowerPoint presentation, and the results of one or more statistical/machine learning models.
Keywords Data Analytics Predictive Modeling machine learning
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal