Welcome to my portfolio website!

Hey folks, I'm
Jade Zhang Data Engineer Data Analyst

Healthcare-focused data architect and analyst with hands-on experience in developing robust pipelines, integrating FHIR and claims data, and optimizing reporting processes. Adept at translating complex datasets into actionable insights that support clinical and business goals.

Download Resume Contact Me
svg image

What do I do

Core Skills

ETL Data Integration Healthcare Data (Epic, FHIR, HIPAA, EHR) Time Series Forecasting Machine Learning NLP Data Visualization

Programming & Tools

Python SQL R PowerShell SSIS Tableau Power BI Git RESTful API AWS dbt

Experiences

2024

Data Architect/AnalystNewYork-Presbyterian Hospital

Led the end-to-end development of a data integration project using Python, SQL, SSIS, dbt, and RESTful APIs to enhance FHIR-based BCDA data with CCLF, improving data completeness. Built and maintained robust ETL pipelines for commercial claims and Epic Clarity EHR data, resolving legacy issues and integrating data into a customized Caboodle database. Improved SQL solutions for commercial supplemental files, boosting HEDIS performance metrics, and supported CMS reporting through data preparation and validation.

2023

Statistical Data AnalystNewYork-Presbyterian Hospital

Built a Python pipeline using regex and NLP to extract over 95% of unstructured data from doctor notes. Developed SQL scripts for HEDIS measures and developed interactive dashboards in Tableau and Power BI to visualize key commercial metrics.

2023

Data Science InternFulton Bank

Developed a keyword-based search tool using Python and PowerShell to efficiently retrieve content from over 1,200 Power BI and SQL reports, improving accessibility for 60+ users. Co-created a machine learning pipeline to forecast cash balances across 204 branches, supporting a utility with projected savings of $5.5–10M annually. The prototype won first place in an internal datathon and advanced toward production deployment.

2021

Graduate ResearcherDrexel University

• Proposed and implemented a bisecting hierarchical clustering algorithm for time series data to forecast college enrollment, improving accuracy by 15% over conventional methods.

Educations

2023

M.S. in Economics and Computer Science

Drexel University

2021

M.S. in Business Analytics

Clark University

2019

B.S. in Applied Mathematics

University of Maryland, College Park

Certificates

HL7 FHIR Implementer (2025)
HIPAA Compliance Certificate (2025)
Epic Caboodle Data Model (2023)
Epic Clarity Data Model (2023)
Epic Cogito (2023)

Projects & Conference Presentation

Some highlights of my work in data, analytics, and engineering.

Choosing Aggregation level for Forecasting and Fairness
Choosing Aggregation level for Forecasting and Fairness
International Symposium on Forecasting
Oxford, England | 07/2022

Developed a bisecting hierarchical clustering algorithm and implemented a hierarchical forecasting scheme using statistical models to improve college enrollment forecasts by 15%, enabling institutions to enhance fairness representation across racial/ethnic groups through data aggregation.

Investigation Potential Bias …
Investigation Potential Bias In the Development of A Typical AI Platform for Heart Transplantation
INFORMS Annual Meeting
11/2020

Utilized multiple statistical tests to investigate if there is a significant bias in the predictive outcomes of a typical heart transplant decision-making platform. Revealed the existence of gender bias and regional bias.

Patient survival rates Prediction
Patient survival rates Prediction
Women in Data Science Datathon in 2020

Predicted patient survival rates based on data from the first 24 hours of intensive care using ensemble machine learning methods, such as XGBoost and LightGBM. Obtained high accuracy and finished in the top 10% of participants.

Get in touch

Feel free to reach out about data engineering, analytics, or healthcare data projects.

szhangjd21[at]gmail.com

Let’s talk

Email Me