Complete IntelligenceData Scientist
May. 2022The Woodlands, Texas, United States• Developed Python scripts to extract data from APIs, load into databases, automate data processing tasks, and build machine learning models with Scikit-learn to predict outcomes, reducing manual data processing time by 80%, and data pulling time by 95%.
• Employed Pandas for data analysis, manipulation, and visualization on datasets with up to 5 million rows. Utilized Git version control to track code changes across a 4-person team. • Analyzed, interpreted, and visualized data using exploratory mathematical and statistical techniques to develop quantitative assessments and solve complex problems, improving prediction accuracy by 10% on average.
• Engineered automation solutions for over 80% of the company's critical data processing scripts, reducing manual oversight needed and significantly improving operational efficiency.
• Assessed code quality during testing to identify and correct errors and optimize performance, reducing program run time by 30%. Implemented new API routes, ORM structures, and refactored over x lines of code to boost application performance by 25%.
• Coordinated project development and code submissions for 30+ software releases using Git/GitHub version control tools. Devised protocols to safeguard proprietary data for Fortune 500 clients. • Managed 3 data science projects simultaneously while delivering high quality results within tight deadlines.