AWS, GCP, Pandas/Numpy, Git, Matplotlib/ggplot/dplyr, TensorFlow, Hive, PySpark, Azure Databricks, PostgreSQL, Tableau, Snowflake
Causal Inference, Applied Mathematics, Predictive Modeling, General Linear Model (GLM), Generalized Linear Model (i.e., Logistic Regression), Recommendation Systems, Frequentist Inference, Bayesian Statistics, Machine Learning (ML), Deep Learning (DL), Feature Engineering, Computer Vision (CV)
Python
SQL
R
Rust
Senior Data Analyst | Modernization and Accessibility
Washington, DC
· Led a cross-functional team in the development of an end-to-end data pipeline which resulted in $10+ million being returned to the organization.
· Work closely with C-Suite/executive leadership to develop an ETL pipeline and ML model for the detection and flagging of potential fraudulent actors.
· Automated three regular reports using python, reducing the workload of the data analytics team.
· Mentored and trained two professional-level data analysts, acting as the point of contact in the absence of the team lead.
· Promote data accessibility through the development of data resources and mentorship of data-interested individuals across the organization.
Program Analyst | Fraud Detection Data Scientist
Washington, DC
· Conducted data querying and anomaly detection methods, identifying a subset of potentially malicious companies. Successfully withheld approximately $40 million from these companies pending further investigation.
· Supporting the migration of 50+ reports from a SharePoint site to Tableau and Posit Connect servers to improve data accessibility.
· Spearhead an initiative to improve company-wide data infrastructure through the procurement of distributed computing software.
· Leading an effort to use machine learning to detect fraudulent agents in the Lifeline and ACP programs. Currently in the data engineering/feature selection phase.
· Query/analyze large (5+ million) program applications, enrollments, and claims data and present insights to organizational leadership, the FCC, and other stakeholders through Tableau dashboards and Posit connect web applications.
Associate Data Scientist | Recommendation Systems
Arlington, VA
· Produced two production grade recommendation models using high quality, reusable python code with an emphasis on scalability.
· Recommendation systems aimed to promote a streamlined procurement process by suggesting similar contracts to private firms aiming to conduct business with federal, state, and local governments.
· Deployed models with Databricks MLFlow for real-time inference and reported model performance metrics in live dashboards which resulted in the development of test strategies and optimizing the models.
· Models implemented one or more conventional data science frameworks for natural language processing (NLP), recommendation systems, and traditional machine learning techniques.
· Created data infrastructures for extraction, transforming, and loading (ETL) data into production models using government API’s, Databricks workflows, and a Hive metastore.
· Conducted data analysis on big data (roughly one million cases) using distributed cloud computing and AWS microservices.
Senior Research Assistant (08/2018-08/2021)
Sacramento, CA
· Chaired roughly 20 quantitative research projects (3-8 projects at a time) from hypothesis to dissemination with the goal of presenting at international, national, and regional conferences.
· Preform advanced statistical analysis and machine learning in R and SPSS.
· Received awards at three separate conferences for the projects’ scientific merit and quality of the presentation.
· Reduced time spent on data cleaning by over 50% by initiating reusable code utilized across team members and projects.
· Conducted consultation sessions on research methods and statistics for over 10 graduate and advanced undergraduate students.
· Mentored over a dozen junior researchers to promote career growth and improve organizational satisfaction.
Business Data Analyst
Sacramento, CA
· Developed weekly dashboards using R, R Markdown, and SPSS to perform A/B tests, regression, and data visualizations on user behaviors and attitudes to achieve stakeholder goals.
· Served as the subject matter expert (SME) for data and led quarterly meetings with organization leadership and stakeholders to support data-driven decision-making.
· Maintained a single database housing more than 10 tables and included all data entering the organization to improve data analysis efficiency.
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.