Vita
Curriculum Vitae (PDF) · Resume (PDF) · Software Carpentry Certification · Data Carpentry Certification
Employment
2021–Present Senior Data Scientist, Karna, Atlanta, GA
- Engineered a document intelligence microservice that automated clinical document extraction (Azure Document Intelligence, Textract) and AI-powered synthetic data generation (GPT-4); deployed on ECS with schema enforcement and data validation to protect downstream quality.
- Built compliant Snowflake data infrastructure and SQL-based ETL pipelines using Python, R, and shell scripting to ingest multi-source clinical datasets and surface opioid use trends, program utilization metrics, and drug co-occurrence patterns supporting national federal opioid response planning.
- Designed and deployed a HIPAA/NIST-compliant ML pipeline for maternal CVD risk stratification on Azure, with automated drift monitoring and a Flask API; migrated from SQLite to PostgreSQL in production; applied causal inference (ITS and diff-in-differences) to measure the program’s impact on emergency care utilization.
- Partnered with data science, research and evaluation, and health communications teams to design and run A/B message testing for CDC NCIRD’s COVID Vaccine Task Force; tested message variants across hesitancy segments, political ideology, and demographics using ordered logistic regression; findings directly shaped national vaccine communication decisions.
- Awards: President’s Award (2023), Technical Achievement Award (2023), Community Engagement Award (2022), Outstanding Publication runner-up (2022), Technical Achievement runner-up (2024)
2021–Present Lecturer, University of Washington, Department of Sociology, Seattle, WA
- Designed and taught applied labs on behavioral and digital trace data analysis (Google Trends, Fitbit, sensor data), data visualization, NLP, and algorithmic fairness; challenged students to interrogate models for potential bias from training data, historical inequities, and deployment context.
- Designed and ran in-class randomized experiments (A/B tests) covering random assignment, hypothesis testing, and power analysis, demonstrating how controlled experimentation underpins data-driven product and policy decisions and where purely observational analysis falls short.
2020–2021 Senior Policy Advisor, Office of Harris County Judge Lina Hidalgo, Houston, TX
- Automated COVID-19 surveillance reporting by replacing hand-transcribed web data and manual multi-source joins with a reproducible R pipeline ingesting DSHS, HCPH, and national datasets, reducing processing latency by 90% and enabling real-time data quality for policymakers.
- Applied statistical modeling to evaluate county-wide housing initiatives, projecting $6 million in annual savings from permanent supportive housing proposals.
2020–Present Principal, Atlas Analytics, Houston, TX
- Built a Python/SQL entity resolution pipeline joining fragmented SBA datasets with merchant registries via a tiered probabilistic matching algorithm (86% recall on a manually labeled hold-out set), enabling downstream customer analytics and market segmentation.
- Built data pipelines integrating a 2.2M-member consumer transaction panel (Earnest Analytics), device mobility data (SafeGraph), and COVID policy records; analyzed user acquisition and retention cohorts to quantify COVID-19’s long-term impact on consumer behavior across 12 categories; acknowledged for research assistance in Oblander & McCarthy, Marketing Science (2023).
2018–2020 Data Scientist, MAANA, Houston, TX
- Partnered with solutions architects to engineer and deploy containerized ML microservices (Docker, Kubernetes) powering a real-time vessel routing optimizer across global multi-port routes, with ingestion pipelines parsing Q88 XML and integrating live weather, war-risk, and port data to cut fleet planning from hours to minutes; cost forecasting on historical trades projected $100M in annual savings.
2017–2018 Postdoctoral Researcher, Università Bocconi, Milan, Italy
- Carlo F. Dondena Centre for Research on Social Dynamics and Public Policy
- Engineered multi-source data fusion pipelines from social media APIs and digital trace data to produce high-frequency population estimates and evaluate policy outcomes at scale.
2016–2017 Program Manager, eScience Institute, Data Science for Social Good, Seattle, WA
- Organized program resources, created student selection process, and scheduled activities.
- Coordinated with industry partners to incorporate real-world data science challenges into projects.
Education
2017 Ph.D., Sociology, University of Washington
- Center for Statistics and the Social Sciences: Certification in Social Statistics
- Dissertation: Developing Computational Approaches to Investigate Health Inequalities
- Advised by: Hedwig Lee (co-chair), Kyle Crowder (co-chair), Emilio Zagheni, Ariel Rokem, and Darryl Holman
2012 M.A., Sociology, University of North Carolina at Chapel Hill
- Carolina Population Center Pre-doctoral Fellow
2009 B.A., Sociology, Princeton University
Affiliations
2019– Regional Affiliate, Center for the Study of Demography and Ecology, University of Washington, Seattle, WA
2017–2018 Postdoctoral Affiliate, Bocconi Institute for Data Science and Analytics, Milan, Italy
Fellowships
| Year | Fellowship |
|---|---|
| 2017 | Summer Institute in Computational Social Science Fellow, Russell Sage Foundation and Princeton University |
| 2017 | Civic Technology Fellow, Microsoft Civic Technology and Engagement |
| 2016 | Pre-doctoral Fellow, Big Data-Scientist Training Enhancement Program, Department of Veterans Affairs, Puget Sound Healthcare |
| 2015 | Data Science for Social Good Fellow, eScience Institute, University of Washington |
| 2011 | Graduate Research Fellow, National Science Foundation Graduate Research Fellowship Program |
| 2010 | Pre-doctoral Fellow, Carolina Population Center, University of North Carolina at Chapel Hill |
| 2008 | Junior Summer Institute Fellow, Public Policy and International Affairs, Carnegie Mellon University |
Publications
Alexander, Monica, Kivan Polimis, and Emilio Zagheni. 2020. “Combining social media and survey data to nowcast migrant stocks in the United States.” Population Research and Policy Review.
Salganik, Matthew, Ian Lundberg, Alexander T. Kindel, Caitlin E. Ahearn, et al. 2020. “Measuring the predictability of life outcomes with a scientific mass collaboration.” Proceedings of the National Academy of Sciences.
Alexander, Monica, Kivan Polimis, and Emilio Zagheni. 2019. “The impact of Hurricane Maria on out-migration from Puerto Rico: Evidence from Facebook.” Population and Development Review.
Filippova, Anna, Connor Gilroy, Ridhi Kashyap, Antje Kirchner, Allison C. Morgan, Kivan Polimis, Adaner Usmani, and Tong Wang. 2019. “Humans-in-the-Loop: Incorporating Expert and Crowdsourced Knowledge for Predictions in Survey Data.” Socius.
Polimis, Kivan, Ariel Rokem, and Bryna Hazelton. 2017. “Confidence Intervals for Random Forests in Python.” Journal of Open Source Software, 2(19), 124.
Marsh, Kris and Kivan Polimis. 2015. “The Lifecourse Perspective in Explaining Racial Residential Segregation.” Chapter 4 in Race, Space and Exclusion: Segregation and Beyond in Metropolitan America, edited by Robert Adelman and Christopher Mele. New York: Routledge.
Turner, Robert W., Asheley Skinner, Eliana Perrin, Kivan Polimis, and Tamera Coyne-Beasley. 2014. “High School Sports Participation: Risk and Protective Factors for Early Adulthood Physical Activity and Obesity in a Representative Longitudinal Study.” Journal of Adolescent Health, 54(2, Supplement).
Software
Polimis, Kivan. 2017. yandex-translater: R package to interface with the Yandex Translate API.
Rokem, Ariel, Kivan Polimis, and Bryna Hazelton. 2016. forest-confidence-interval: Confidence intervals for Forest algorithms.
Presentations
2022 “Introduction to Application Programming Interfaces.” Public Health Data Workshop, Harris County Public Health. Houston, TX.
2019 “Combining Facebook and traditional surveys: A case study with Hurricane Maria and Puerto Rican out-migration” (with Emilio Zagheni, Monica Alexander, Ingmar Weber, and Francesco Billari). Center for Statistics and the Social Sciences, University of Washington. Seattle, WA.
2019 “The impact of Hurricane Maria on out-migration from Puerto Rico: Evidence from Facebook data” (with Monica Alexander and Emilio Zagheni). Population Association of America. Austin, TX.
2018 “Humans-in-the-Loop: Incorporating Expert and Crowdsourced Knowledge for Predictions in Survey Data” (with Anna Filippova, Connor Gilroy, Ridhi Kashyap, Antje Kirchner, Allison C. Morgan, Adaner Usmani, and Tong Wang). International Institute for Social Studies, Erasmus University. The Hague, The Netherlands.
2018 “Can social media assess demographic variations in physical activity attitudes?” Young Demographers Conference. Prague, Czech Republic.
2018 “Comparing typological approaches to family homelessness.” Alpine Population Conference. La Thuile, Italy.
2017 “Can social media be used to assess demographic variations in physical activity attitudes?” Population Association of America. Chicago, IL.
2017 “Social Media and Demographic Methods” (with Emilio Zagheni and Lee Fiorio). Workshop at the Population Association of America. Chicago, IL.
2016 “Web, Social Media Data and Demographic Research Workshop: Twitter Module” (with Emilio Zagheni and Monica Alexander). European Population Conference. Mainz, Germany.
2016 “Social Media and Demographic Methods Workshop: Twitter Module” (with Emilio Zagheni, Nina Cesare, Charles Lanfear, and Joan Ryan). Population Association of America. Washington, D.C.
2012 “Junk in the Trunk: Evaluating the Relationship between Body-Mass Index and Interracial Dating.” Add Health Users Conference. Bethesda, MD.
2011 “Adolescent Experiences & Adult Neighborhood Attainment” (with Kris Marsh and Kyle Crowder). Population Association of America. Washington, D.C.
Teaching
2021– University of Washington, Department of Sociology — Data and Society (SOC 225)
2016 University of Washington, CSSS — Quantitative Techniques in Sociology (CSSS 507/SOC 506), Graduate Teaching Assistant
2015 University of Washington, Department of Sociology — Applied Social Statistics I & II (SOC 504 & SOC 505), Graduate Teaching Assistant
Research Positions
| Years | Position |
|---|---|
| 2016–2017 | Research Assistant, Center for the Study of Demography and Ecology, University of Washington |
| 2016–2016 | Research Assistant, Center for Evaluation and Research for STEM Equity, University of Washington |
| 2015–2016 | Research Assistant, eScience Institute, Gates Foundation, University of Washington |
| 2013–2014 | Data Analyst, San Francisco 49ers |
| 2009–2010 | Research Assistant, Office of Population Research, Princeton University |
Consulting and Management
| Years | Position |
|---|---|
| 2017 | Program Coordinator, eScience Institute, Data Science for Social Good |
| 2016–2017 | Consultant, King County Auditor’s Office, Seattle, WA |
| 2016 | Consultant, eScience Institute, Data Science for Social Good |
| 2014 | Product Development Consultant, Seremedi, Houston, TX |
| 2013–2014 | Special Projects Manager, Councilman Ed Gonzalez, Houston City Council |
Technical Skills
| Instructor | Software Carpentry Instructor, Data Carpentry Instructor |
| Software | R, Python, Spark, GraphQL, Docker, Jira, Stata, Microsoft Office Suite |
| Tools | Git, LaTeX, shell scripting, Amazon Web Services, Microsoft Azure |
Professional Service
Memberships: American Sociological Association, Population Association of America, International Union for the Scientific Study of Population, Cascadia Urban Analytics Cooperative, Association for the Advancement of Artificial Intelligence
Refereeing: Population Research and Policy Review, Population and Environment, Social Forces, Socius, Urban Affairs
Volunteer
2023– Communications Vice Chair, Princeton Alumni Association of Houston
Media and Awards
| Year | |
|---|---|
| 2024 | Karna — Technical Achievement Award runner-up |
| 2023 | Karna — President’s Award |
| 2023 | Karna — Technical Achievement Award |
| 2022 | Karna — Community Engagement Award |
| 2022 | Karna — Outstanding Publication Award runner-up |
| 2018 | Online calculator to help tackle disparities in the criminal justice system in Washington state |
| 2017 | My eScience Experience |
| 2017 | GitHub for Collaboration |
| 2016 | Legal Financial Obligations |
| 2015 | Budding UW Data Scientists Use Their Powers for Social Good |
| 2015 | UW students put data science skills to use for social good |
References
Kyle Crowder, Professor, University of Washington — kylecrow@uw.edu
Emilio Zagheni, Managing Director, Max Planck Institute for Demographic Research — office-zagheni@demogr.mpg.de
Sarah Stone, Executive Director, eScience Institute, University of Washington — sstone3@uw.edu