Data
Level | Data Scientist | February 2021 - Present
- Perform ad hoc analyses with SQL using a diverse range of data sets,
including EDI dental claims data, card transaction data, sessionized
customer event data from web and mobile apps, and bi-temporal ledger
data.
- Strategize cross-functionally with sales, finance, and operations
teams to inform product roadmap through standing up core dashboards of
key performance metrics, conducting quantitative analyses of pain
points, and assembling qualitative findings based on interviews with
stakeholders.
- Partner with engineering to design a new reporting architecture,
including collecting system requirements from a data modeling
perspective, determining user stories to inform test cases, and
reviewing warehousing frameworks to ensure robust analytical
capabilities.
- Develop and test dbt models for analytical use cases with dbt
alerting for data health. Use Jinja macros to transform and document
data stored as JSON blobs outputted from protobuf messages into BigQuery
data structs.
- Implement custom Python ETLs using Kubernetes to extract data from
third party APIs for analysis in Jupyter notebooks (including developing
risk rules through assessing statistical performance metrics of
risk-related features).
- Led team in company-wide migration of data assets from Periscope to
Looker, using LookML development to enable self-service analytics with
engineers and non-technical stakeholders. Implemented trainings and
office hours to familiarize teams with Looker for data-driven planning
of team goals.
- Core member of the DEIB+ team, creating virtual events and resource
guides to educate and celebrate diversity across Level and
customers.
Crossix, A Veeva Company | Senior Analyst, Marketing Analytics |
June 2019 - January 2021
- Owned over 30 end-to-end analyses that evaluated the impact of
digital marketing on brand conversions, retention, and LTV. Queried and
interpreted claims, EHR, and drug prescription data insights with SQL to
communicate actionable and scalable campaign recommendations for
marketing optimizations.
- Developed visualization dashboards, presented findings, and
translated technical processes to stakeholders.
- Partnered with marketing, product, and client services teams to
scope projects and visualize data for client workshops and industry blog
posts that assess the impact of COVID-19 on marketing trends.
Digital Health
NYSDOH’s AIDS Institute | Digital Health Intern | Jan 2018 - June
2019
- Scraped/analyzed comments from an online forum with R to assess the
impact of a web-based comic, “Tested,” that aims to educate young
readers about health topics. Used tidyverse, ggplot, and tidytext to
visualize and aggregate insights into markdown reports.
- Created and managed social media strategies for the Y Get It? (YGI)
project, which focuses on linking HIV-affected youth to care through a
mobile application intervention and the comic serial.
- Developed and led presentations on new tools and technologies for
digital health promotion.
Skills
- Data analysis (A/B testing, data mining)
- Fluent in ETL pipelines and dimensional modeling
- Expert in SQL (especially BigQuery)
- R (tidyverse, ggplot, flexdashboards)
- Python (pandas, numpy, seaborn, sklearn)
- Looker/LookML development
- Git/Github version control
- dbt development and testing
- Analytics engineering
Publications
- Spillane, T.E., Wong, B.A., Giovenco, D.P. (2020). Content analysis
of instagram posts by leading cannabis vaporizer brands. Drug and
Alcohol Dependence, https://doi.org/10.1016/j.drugalcdep.2020.108353
- Giovenco, D.P., Spillane, T.E., Wong, B.A., Wackowski, O.A. (2019).
Characteristics of storefront tobacco advertisements and differences by
product type: A content analysis of retailers in New York City, USA.
Preventive Medicine, 123, 204-207.
Education
Master of Public Health | Columbia University Mailman SPH
- Department: Sociomedical Sciences
- Certificate: Applied Biostatistics
- Awards: Dr. Jack Elinson Scholarship recipient
- Thesis: How Data Determines Health: A Qualitative Research
Proposal Exploring Perceptions of Big Data in Public Health
Bachelor of Science | University of California, Los Angeles
- Major: Cognitive Science
- Specialization in Computing
- Awards: Magna Cum Laude, Dean’s Honors List
Hackathons
- Winner of the Community Choice award and the Most Innovative
Contribution award.
- Outlined a framework for developing and reporting a “sustainability
score” that would be used to grade the supply chain of a consumer
product. The team also developed a proof-of-concept widget that could be
added as a browser extension to report these scores on consumer
websites.
- Contributed to the writing of the overarching framework and helped
generate an example of an application for the project (the iPhone).
- Joined the 2020 discussions to help facilitate project management
and next steps for future Collabathons.
Datakind + Microsoft Virtual DataDive: Applying AI to Societal
Challenges in US Cities | Miami Project | Oct. 2019
- Member of the Miami Project team, comprised of volunteer data
scientists and data analysts in collaboration with the Code for Miami
organization to implement AI in cities.
- Engaged in exploratory data analysis using ggplot and tidyverse in
R, as well as built/tested machine learning models using pandas and
scikit-learn in Python. Also assisted with standing up an API for the
project partner to understand the variables that impact turnaround time
for applications to develop affordable housing.
Mount Sinai Health Hackathon 2019 | Team Blackbox AI |
Oct. 2019
- Designed and created a website that uses video lessons, interactive
statistical visualizations, and written descriptions to educate
clinicians on the application and interpretation of artificial
intelligence in healthcare settings.
- Brainstormed project execution and wrote HTML in Dash to create a
functioning mock-up of the website (domain no longer active).