Data Science Driven Aircrew Performance Measurement and Proficiency System

Using integrated teams of Operational Analysts experienced with Naval aircrew training and Software Engineers experienced in developing dynamic analysis and reporting tools for aviation, a pragmatic and scalable approach to aircrew performance assessment and proficiency is proposed. Initial techniques to incorporate data fusion of disparate data sources are summarized from past experience and existing software solutions. These techniques can be applied to aircrew performance assessment to reduce instructor work-load while also increasing the speed and accuracy of assessment. A process outline to decompose training scenarios in a manner that supports automation, human-in-the-loop techniques, and advanced data science is presented for further refinement during the research. The methodologies proposed for research all include the ability to scale across multiple platforms, training devices, training missions, and aircrew configurations through innovative application of modern programming paradigms. The end result is a design realizing this innovation in a user-oriented toolset supporting actionable feedback in a performance assessment and proficiency system.