• Built neural network NLP text classifier and continuous improvement pipeline in Python. • Engineered features from NoSQL database using Presto to enhance supplier risk assessment models. • Devised and ran natural experiment and conducted ANOVA to determine that a process change would result in saving over 500 hours of case review time each month. • Conducted periodic ad hoc analyses with custom SQL queries to resolve discrepancies in reported data. • Developed logistic regression models for throughput and quality analysis. • Developed dominance analysis to identify top predictors driving case review throughput and quality. • Implemented fact and dimension tables to enable tracking of case review business metrics. • Created R and Rmarkdown dashboard to track key performance metrics. • Supported and extended dashboard features with additional visualizations.

My Education

Take a look at my formal education

Master of Science in Data ScienceRochester Institute of Technology | 2024

Bachleor of Science in Computer ScienceColorado State University | 2008

Master of Science in Chemical EngineeringColorado State University | 1996

About Me

I'm a data scientist with over 6 years of experience, focused on ethical data use, solving problems with machine learning, and translating technical insights. With a background in software engineering, I hold an MS in Data Science and have a passion.

Create Your Data Portfolio for Free