Hi, I'm Arthur.

I am a Data Science Lead specializing in scalable measurement systems, causal inference, and the infrastructure that turns complex data into decisions that actually change things. My MS in Scientific Computing and MA in Econometrics give me the range to move fluidly between rigorous statistical modeling and high-performance engineering across the full data lifecycle. My background as an educator is the glue that ties analytics to the business and its decision makers. Helping people and organizations thrive is my number one motivator.

Examples of Work Impact

Penn Cobalt

Photo by Thirdman on Pexels

Penn Cobalt is a Penn Medicine-developed mental health platform serving 40,000+ employees, offering automated intake assessments, therapy scheduling, expert-facilitated group sessions, and on-demand self-help resources across a range of content modalities.

As the platform's analytics lead, I built and maintained the GA4/GTM implementation, managed PostgreSQL and BigQuery data pipelines, and developed the KPIs that characterized engagement, service utilization, and treatment outcomes via validated clinical assessments. I worked with stakeholders across product, engineering, and clinical teams to translate measurement requirements into specifications and findings into decisions.

The platform reached 70-80% sustained utilization within the first two years, prompting expansion to Penn student and patient populations and a SaaS model now operational at five partner universities.

Bluecoats Program

Photo by RDNE Stock project on Pexels

Bluecoats is a closed-loop, human-centric measurement and response program I designed and built from scratch at Penn Medicine to systematically improve employee wellbeing, streamline operations, and strengthen the financial health of the organization.

The program spanned the full arc from data collection to organizational change: automated assessment of large-scale employee surveys, hybrid continuous listening combining staff interviews with digital tools, personalized recommendations and decision support, capacity building through data literacy initiatives, and transparent program evaluation via audience-specific dashboards and bidirectional communication channels. 

In piloting Bluecoats with a single emergency department, I identified an untapped data source and tens of thousands of dollars in monthly losses traced to an overlooked equipment failure in one supply closet. By translating that analysis into a compelling narrative for executive leadership, I earned the trust and resources to expand the program to the highly complex Department of Medicine and, ultimately, organization-wide.

Yelp Health Data Curation Pipeline

Photo by Tima Miroshnichenko on Pexels

The Yelp Health Data Curation Pipeline is a foundational component of Penn Medicine's CHTI AWS data infrastructure, an automated system I designed and built to extract, process, store, and monitor Yelp's entire database of healthcare-related facilities and reviews at scale.

The pipeline handles the full data lifecycle: extracting Yelp-provided daily database snapshots from S3, processing raw JSON into validated, analysis-ready master files for facilities, facility categories, and reviews, and managing storage across tiered S3 classes to minimize cost. I implemented IAM-controlled access and permissions to govern data integrity and streamline distribution to internal teams, external researchers, and independent investigators. An automated weekly monitoring and reporting system ensured data quality over six-plus years of continuous operation.

The result was a production-grade research asset that ran for six-plus years without a single day of data loss, supporting 20+ peer-reviewed publications in top-tier journals and serving as a high-value source of patient perception data for health systems looking to improve care delivery. Its most consequential output was a real-time COVID-19 symptom tracker that identified emerging symptoms before the CDC.

Professional Experience

Subject Matter Expert and Beta Tester
SweetRush Inc. - Contract
San Francisco, CA - Remote
September 2025

Data Scientist
University of Pennsylvania Health System
Center for Healthcare Transformation and Innovation
Philadelphia, PA
February 2018-August 2024 

Machine Learning and Data Scientist Intern
Aramark Corporation
Philadelphia, PA
May-August 2016

Business Intelligence Analyst
Banner Promotions
Philadelphia, PA
August 2014-February 2018

Physics Educator
Paul VI High School
Haddonfield, NJ
September 2010-June 2014

Education

MS, Scientific Computing
Rutgers University–Camden
October 2017

MA, Economics
Concentration in Applied Econometrics
University of Delaware
August 2010

BA, Physics
University of Delaware
May 2008

Certifications

Deep Learning With Keras and Tensorflow
IBM–Coursera Digital Certificate
October 2025

Introduction to Deep Learning and Neural Networks With Keras
IBM–Coursera Digital Certificate
August 2025

Key Skills

Programming
Python - PyData Stack, SQL, Java,
C, PySpark, API, geospatial, git

Statistics
bayesian, descriptive, inferential, predictive, causal, mixed-effects

Business Platforms
MS - Power Automate, Apps, BI;
docker, github, gitlab, GA4, GTM

Visualization
matplotlib, seaborn, plotly,
dash, panel, flask

Machine Learning
supervised, unsupervised, RL, DL, recommendation, time series, uplift

Cloud Platforms
AWS - S3, EC2, EFS, R53, IAM, 
Athena, Redshift; Azure, GCP

High-Performance Computing
parallel / distributed, CPU / GPU,
data mining, algorithm optimization

NLP
text mining, topic modeling, LDA, sentiment, text summarization

Data Platforms
JupyterLab, Databricks, Stata,
Hugging Face, Keras, TF, PyTorch

Select Publications

JMIR AI •

Association Between Online Reviews of Substance Use Disorder Treatment Facilities and Drug-Induced Mortality Rates: Cross-Sectional Analysis

Conclusions: Lower online ratings of SUD treatment facilities were associated with higher drug-induced mortality at the state level. Elements of patient experience may be associated with state-level mortality. Identified themes from online, organically derived patient content can inform efforts to improve high-quality and patient-centered SUD care.
JMIR Infodemiology •

State and Federal Legislators’ Responses on Social Media to the Mental Health and Burnout of Health Care Workers Throughout the COVID-19 Pandemic: Natural Language Processing and Sentiment Analysis

Conclusions: State and federal legislators use social media to share opinions and thoughts on key topics, including burnout and mental health strain among health care workers. Variations in the volume of posts indicated that a focus on burnout and the mental health of the health care workforce existed early in the pandemic but has waned. Significant differences emerged in the content posted by the 2 major US political parties, underscoring how each prioritized different aspects of the crisis.