Data Scientist · Data Engineer · Developer

I'm Noha, a data professional and developer based in Houston with an M.S. in Computer Science.

I enjoy working with messy, disconnected data; figuring out what's wrong with it, cleaning and restructuring it, and building systems that make it reliable and useful.

I'm currently focused on data engineering, data science, analytics, master data management, healthcare data, and applied AI.

Building a healthcare provider master data system using CMS NPPES, Python, SQL, Pimcore, and Docker to integrate and reconcile provider records across simulated EHR, HR, and credentialing systems.

Python SQL Pimcore Docker Data Quality MDM

Analyzing NHANES data to identify demographic, lifestyle, and routine health factors associated with an elevated likelihood of diabetes and develop interpretable machine learning models for risk screening.

Python pandas Machine Learning Healthcare Data NHANES

Analyzed New Jersey education data to identify and compare Title I schools, districts, student enrollment, and geographic trends.

Python pandas Data Analysis Data Visualization

Built an accessibility-focused language learning application that uses Mathpix OCR and AI to extract conversations from images and generate adaptive language-learning support.

TypeScript OCR AI React

Built a full-stack TypeScript web application that retrieves and displays astronomy content using NASA's APOD API.

TypeScript React Node.js REST APIs

_{Thanks for stopping by ☁️}