Christopher Bui Email & Phone Number

New York, Ny, Us

Boston, Ma, Us

Long Beach, California , Us

• Developed optimized SQL queries on the Microsoft Azure Data Platform to analyze patient EHR and claims data, enabling insights into healthcare trends and client behavior.• Led development of Attribution Models, CART and Deep Neural Network classifiers using PyTorch, to predict high-risk patients for medication non-adherence with improved precision.• Deployed machine learning models in production, evaluating their performance to enhance the identification of members eligible for healthcare plans through AUC-ROC metrics.

Irvine, Ca, Us

• Maintained integrity of end-to-end data pipelines by performing data engineering using PySpark, including data validation, preprocessing, and transformation of clinical KPI datasets, ensuring consistent schema alignment for downstream analytics.• Optimized interactive data visualizations by enhancing Python Dash Plotly dashboards, reducing latency and improving user experience for clinical stakeholders.

Hercules, Ca, Us

• Developed optimized SQL queries in Snowflake to accelerate dataset preparation for PowerBI dashboards built using DAX language.• Conducted profit margin analysis across the company's product portfolio to identify actionable KPIs, improving product strategy.

Laurel, Maryland, Us

• Built a scalable ETL data pipeline in Python to preprocess environmental sensor data from hospital operating rooms.• Developed regression and clustering models to predict hazardous operating room conditions, improving patient safety protocols.• Leveraged High Performance Computing (HPC) clusters with SLURM on Linux to run SARS-CoV-2 protein-protein docking simulations.• Analyzed Covid-19 personal protective equipment inventory using PySpark, identifying supply chain bottlenecks.• Created Standard Operating Procedures (SOPs) for field-testing IoT hardware that predicted core body temperatures in real-time.

St Paul, Mn, Us

• Leveraged PySpark and NTLK on AWS to preprocess large-scale parquet text files containing medical records to • Designed NLP models to generate text embeddings of ICD-10 medical codes, enhancing medical code recommendation accuracy.

New York, Ny, Us

• Completed an intensive 12 week Data Science Bootcamp focused on machine learning, statistical modeling, project design, and communication.

San Diego, Ca, Us

• Utilized Stanford BioDesign Method to identify ineffective and costly practices in the field of Psychiatry• Designed solution to reduce schizophrenic readmission rates by 5%• Developed methods of engaging STEM students into the field of entrepreneurship

La Jolla, Ca, Us

• Managed experiments and recorded data• Performed routine lab maintenance• Research focused on analyzing participants' purchasing habits and quality of decisions in response to external stimuli

M.S., Bioinformatics

Biophysics B.S., Physics

Entrepreneurship Minor