J-Byrd is a data scientist and business intelligence SME in our Defense rapid prototyping team, where his natural curiosity, analytical mind, and ability to count large piles of toothpicks at parties are brought to bear on some of the Department’s biggest data integration problems. 

With JSL Defense, J-Byrd’s current focus involves risk quantification both in theory and application. His formulas are designed to provide interpretive and standardized risk projections that will better inform military decisions. He also develops algorithms to implement these formulas in real time for tracking risk and comparing the benefits and drawbacks of potential risk treatment options.  

His interest in data science began while taking a machine learning course through the UCLA Physics department, where he gained an appreciation for feature selection and feature engineering to achieve accurate models. He has since become intimate with common data science Python libraries, leveraging these libraries in his physics work and previous contracted work.  

As an undergraduate as UCLA, he spent countless hours tutoring physics and mathematics at both the high school and college level. His summers were spent self-teaching Python and developing a deeper understanding of vector calculus and linear algebra. Some of his current intellectual interests include stochastic processes and supervised machine learning models. 

In his free time, J-Byrd usually plays chess or studies chess theory. He has written a Python module with functionality for generating chess variation trees and has additionally worked on data analysis software for acoustics.