The record

Seven years of making data behave

The plain account: where I have worked, what I did there, and what it changed. Everything here is something I am glad to be asked about.

Experience

November 2024 to present

Senior Data Quality and Access Specialist

California Department of Health Care Access and Information (HCAI), Cost Transparency section. Sacramento, California.

Analyze large health care claims and enrollment datasets in California's all-payer claims database using SQL and Python (Pandas), assessing overall data quality and completeness.
Reduced data discrepancies by 95% by developing validation and record-matching rules in SQL and Python.
Automate data cleaning and validation processes, replacing manual review steps.
Build and maintain Tableau dashboards for consistent tracking of data quality, and present findings to leadership and at meetings and conferences.
Conduct detailed analyses of specific health care topics and summarize the findings and recommendations for leadership.
Design trend and forecasting analyses that support legislative and regulatory decisions.
Communicate data quality findings to the team that works directly with data submitters, so that issues are corrected at the source.
Work regularly with technology vendors to resolve data and system issues and recommend improvements.

January 2020 to November 2024

Data Administrative Specialist

City University of Seattle. Seattle, Washington.

Designed and built more than 25 interactive Tableau and Power BI dashboards covering enrollment, retention and academic performance, and presented them to university leadership monthly. The work contributed to a 12% increase in student retention and a 15% rise in alumni engagement.
Automated more than 20 accreditation reports using SQL and Python, saving over 100 hours of manual work each year, and worked with five departments to keep the data consistent across every reporting requirement.
Developed and maintained five Microsoft SQL Server and Microsoft Access databases covering more than 10,000 student academic records in full FERPA compliance, with Python validation checks and automated error reporting.
Wrote more than 50 optimized SQL queries and stored procedures, cutting report generation time by 50%.
Worked with the IT team to identify and resolve database performance issues.
Promoted from Administrative Assistant to Data Administrative Specialist within two years.

March 2019 to December 2019

Junior Data Analyst

Coding Dojo, Inc. Bellevue, Washington.

Analyzed performance data for more than 5,000 bootcamp students in Python and SQL, identifying factors behind an 18% improvement in retention and a 14% increase in job placement.
Built more than 10 Tableau dashboards tracking 20 student-success measures, which made early help for at-risk students possible.
Maintained three SQL Server databases of student performance data, with data quality checks and error handling.
Presented exploratory analysis (Pandas, NumPy, Matplotlib) to the executive team each quarter; the curriculum changes that followed raised student satisfaction scores by 28%.
Ran seven training sessions on SQL, Python and data analysis for non-technical staff.

March 2018 to February 2019

Data Science Intern

CB Therapeutics, Inc. Remote.

Explored experimental data in Pandas and NumPy and identified factors behind a 25% improvement in experiment success rates, worth about $50,000 a year in savings.
Automated the collection and organization of data from more than 10 research projects in Python, halving manual processing time.
Built more than 20 visualizations and a set of reusable templates in Matplotlib, which cut report preparation time by 60%.

Education

2024

Master of Science in Data Science

City University of Seattle. Emphasis in Artificial Intelligence. GPA 4.0, Summa Cum Laude, Phi Kappa Phi.

Coursework in machine learning and deep learning, data mining, statistics, big data architectures, cloud computing, and data management and governance.

2019

Bachelor of Arts in Anthropology

Central Washington University. Cultural and linguistic anthropology. GPA 4.0, Summa Cum Laude.

"Our predecessors in all fields of science had once been content to work from the scattered observations of non-specialists and the unfounded declarations of ancient writers, rather than from empirical evidence."

From my shelfMarie Brennan, In the Labyrinth of Drakes

Skills

SQL
Python (Pandas, NumPy, Scikit-learn)
Tableau
Power BI
Microsoft SQL Server
MySQL
Microsoft Access
R
Microsoft Excel
Trend and forecasting analysis
Data validation and root cause analysis
All-payer claims and enrollment data

I also build with large language models and vision models at home, and I keep notes on what breaks. The case files are the evidence.

Languages

RussianNative
UkrainianNative
EnglishNative-level
GermanLimited working
ChineseLimited working
KoreanLimited working