Download Resume | Download CV

EDUCATION 🎓

MSc. Data Science for Public Policy, Hertie School of Governance, Berlin (2021-2024)

  • Interdisciplinary program focusing on applying data science to societal problems
  • Receiving merit-based partial tuition waiver
  • Expected graduation: June 2024

B.A. Economics (with honors), Pepperdine University, Los Angeles (2015-2019)

  • Thesis: “Effects of Foreign Exchange Rates on US-Japan Trade Relations”

PROFESSIONAL EXPERIENCE đź’Ľ

Student Researcher, Mercator Research Institute (MCC), Berlin (2024-present)

  • Working with the Applied Sustainability Science Group to enhance evidence synthesis through the development of a living map of scientific literature on climate change and human health
  • Developing both supervised and unsupervised machine learning models to correctly identify and categorize scientific literature on climate change and human health using Python
  • Conducting citation network analysis to map the interconnectivity of scientific publications on climate change and human health

Teaching Assistant, The Hertie School, Berlin (2023-2024)

  • Led weekly lab sessions for the Introduction to Data Science course to demonstrate hands-on application of course concepts
  • Educated students on key data science tools and programming languages, such as GitHub and R
  • Prepared course materials detailing best practices for collecting, cleaning, and analyzing data

Junior Data Scientist, CPC Analytics, Berlin (2022-2023)

  • Assisted WHO personnel in setting up a global surveillance system and the development of a web-based Shiny application using R to inform both WHO decision-makers and the wider public
  • Conducted in-depth analyses of the epidemiological characteristics, risk factors, and demographic trends surrounding the 2022-23 mpox (formerly known as monkeypox) outbreak using R and the tidyverse, the outputs from which were incorporated into bi-weekly Acute Events Management presentations, bi-weekly situational reports, three quarterly risk assessments, and three quarterly Emergency Committee meetings
  • For three months, served as the sole data scientist for WHO’s mpox data warehouse which involved maintaining XML and SQL data pipelines for six WHO Regional Offices, configuring public and private APIs, and creating Excel templates with built-in data validation to facilitate data uploads by end users
  • Utilised Bayesian statistics and R programming language to generate short-term projections for 27 countries’ respective mpox case counts and reproduction numbers (R~t~) to inform WHO personnel
  • Contributed to the development of two R packages to assist WHO personnel with performing common data science tasks such as querying WHO servers, cleaning epidemiological data, and generating data visualisations

Procurement Analyst, U.S. Space Force, Los Angeles (2019-2021)

  • Procured supplies and services necessary to support $800M National Security Space Launch Services portfolio
  • Conducted market research, analyzed historical cost & pricing data, and performed quantitative analyses to establish negotiation objectives

Director of Education, Pepperdine Model United Nations, Los Angeles (2018-2019)

  • Led weekly 1hr 30min sessions to train 26 undergraduate and graduate students in research, policy analysis, memo writing, public speaking and advanced debate skills
  • reports on a diverse set of topics such as external debt sustainability, financing for renewable energy projects, and the economic impact of intellectual property transfer

Economics Tutor, Pepperdine University, Los Angeles (2018)

  • Tutored 15 undergraduate students in collegiate-level macroeconomic theory
  • Held group study sessions ahead of mid-terms and final exams

Procurement Intern, U.S. Air Force, Colorado Springs (2018)

  • Received formal on-the-job training in market research, price & cost analysis, and negotiation
  • Assisted with the procurement of IT infrastructure upgrade for U.S. Air Force Space Command

Research Assistant, Pepperdine University, Los Angeles (2017)

  • Conducted qualitative study examining student perspectives on diversity at Pepperdine University
  • Performed literature review, ran 12 focus groups, and transcribed student interviews
  • Generated report synthesizing findings and presented key takeaways at research symposium

Associate Editor, Pepperdine University, Los Angeles (2016-2017)

  • Evaluated submissions for the Pepperdine Journal of Communication Research
  • Nominated articles for publication based on academic rigor, grammar, spelling, syntax, and organizational structure

Publications đź“ť

Hoxha A,Kerr SM, Laurenson-Schafer H, Sklenovská N, Mirembe B, Nezu I, et al. Mpox in Children and Adolescents during Multicountry Outbreak, 2022–2023. Emerging Infectious Diseases. 2023 Oct; 29(10):2125-2129. doi:10.3201/eid2910.230516.

Laurenson-Schafer H, Sklenovská N, Hoxha A, Kerr SM, Ndumbi P, Fitzner J, et al. Description of the first global outbreak of mpox: an analysis of global surveillance data. The Lancet Global Health. 2023 Jul; 11(7):e1012-e1023. doi:10.1016/S2214-109X(23)00198-5.

PROJECTS 📦

Tutorial: Retrieval Augmented Generation with Citation | Deep Learning (GRAD-E1394)

  • Developed a Python tutorial on how to implement a Retrieval Augmented Generation with Citation (RAG+C) chatbot to address the challenge of knowledge management in government
  • RAG+C provides Large Language Models (LLMs) with additional context sourced from an external database which significantly improves response accuracy and avoids hallucinations
  • The tutorial demonstrates fundamental RAG+C concepts and deploys a chatbot on Hugging Face

EU Procurement Network Analysis | Applied Network Analysis (GRAD-E1426)

  • Examined network dynamics within EU public procurement markets based on a dataset of 234 public procurement markets across 26 European countries from 2008-2016 using Python
  • Networks comprised buyers and suppliers of public contracts
  • Investigated network characteristics associated with perceived government corruption

Israel-Hamas War News Coverage Text Analysis | GRAD-E1282

  • Investigated how news coverage of Israel-Hamas War evolved over time and the extent to which news coverage varied by news source by conducting a text analysis with R
  • Sourced 4,000+ articles from various news sources including the New York Times, Al Jazeera, and Die Welt published in the weeks immediately preceding and following Hamas’s October 7 attack
  • Employed topic modeling and sentiment analysis to analyze trends in news coverage by group

Detecting COVID-related Fake News with Machine Learning | Maching Learning (GRAD-24)

  • Used the Covid-19 Fake News dataset comprising 10,700 Covid-related social media posts labeled either “real” or “fake” to build a fake news detection algorithm with Python
  • Measured the extent to which the fake news detection algorithm degraded over time due to temporal shifts in content
  • Authored blog post detailing methods and findings

Validating COVID Self-Tests with Image Recognition | Data Structures & Algorithms (GRAD-C9)

  • Developed an algorithm capable of validating COVID self-test using image recognition with Python
  • Used data from the MNIST database of handwritten digits, a collection of 70,000 examples, to train the Machine Learning algorithm to recognize handwritten serial numbers and COVID test results

UK COVID Dashboard Disaggregated by Age Group | Intro to Data Science (GRAD-C11)

  • Hosted and deployed dashboard with R and Shiny to track COVID case rates in England with the added option to disaggregate by age group
  • Extracted COVID case rate dataset and boundary data for all 309 local authority districts from UK government APIs

Workshop: Interactive Graphics with Plotly | Intro to Data Science (GRAD-C11)

  • Hosted a session on building interactive graphics with R and plotly for the Tools for Data Science Workshop at the Hertie School
  • Provided conceptual overview, demonstrated plotly’s key features, offered practice materials and additional resources

Effects of FOREX Rates on U.S.-Japan Trade Relations | Applied Econometrics (ECON 410)

  • Quantified the extent to which fluctuations in the U.S. dollar-Japanese yen (USD-JPY) foreign exchange rate impact bilateral trade between the U.S. and Japan using R
  • Constructed a dataset using U.S. Census Bureau and U.S. Federal Reserve data
  • Conducted Granger causality tests, impulse-response tests, and vector autoregression (VAR) analyses to test hypothesis

Technical Competencies 🛠️

R

  • Led lab sessions for the Hertie School’s Introduction to Data Science course where R served as the programming language of instruction
  • Passed LinkedIn Skill Assessment for R (Top 5%)
  • Frequently use R to clean, wrangle, model, and visualize data for projects and papers
  • Advanced familiarity with tidverse (tidyr, dplyr, ggplot), sf (geocoding), and Shiny packages

Python

  • Utilize Python to prepare data, fit machine learning models, work with text data, perform network analyses, and visualize results
  • Advanced experience with pandas, numpy, sklearn, matplotlib and seaborn packages

SQL

  • Certificate in Using Databases with Python
  • Experience with creating, retrieving, updating, and deleting database information with SQL
  • Used SQL to create a database of web-scraped geo-location data for data visualization project

Machine Learning

  • Fine-tuned an open-source Large Language Model (LLM) on corpus of nearly 3,500 technical documents to build a chatbot capable of answering technical questions while citing its sources
  • Developed a ML algorithm capable of validating COVID-19 rapid self-tests using image recognition
  • Currently implementing a project that combines ML and Natural Language Processing to detect fake social media posts about public health

Other Coding Skills

  • Git/GitHub/GitLab
  • Jupyter Notebook/R Markdown/Quarto
  • Command Line/Terminal/Bash/Zsh
  • Shiny Apps/Streamlit/Dashboards
  • Web-scraping (HTML/CSS/XML)
  • API Requests
  • Regex
  • LaTeX

MS Office

  • Advanced experience with using Excel formulas, functions, and pivot tables
  • Deep familiarity formatting reports, incorporate graphs & charts, and create mock-ups in Word
  • Routinely deliver presentations, trainings, and briefings using PowerPoint

RELEVANT COURSEWORK đź“š

  • Deep Learning (GRAD-E1894) | Fall 2023
  • Applied Network Analysis (GRAD-E1426) | Fall 2023
  • Governance & Politics of Artificial Intelligence | Fall 2023
  • Text as Data (GRAD-E1282) | FAll 2023
  • Machine Learning (GRAD-C24) | Spring 2022
  • Mathematics for Data Science (GRAD-C23) | Spring 2022
  • Causal Inference (GRAD-C22) | Spring 2022
  • Introduction to Data Science (GRAD-C11) | Fall 2021
  • Data Structures & Algorithms (GRAD-C9) | Fall 2021
  • Applied Econometrics (ECON 410) | Spring 2019

RECOGNITION 🏆

  • Merit-based Tuition Waiver, Hertie School (2021-2024)
  • Contracting Civilian-in-Training of the Year, U.S. Space Force (2020)
  • Regents’ Scholar Award (Top Academic Scholarship), Pepperdine University (2015-2019)
  • Cum Laude, Peppperdine University (2019)
  • Best Delegate Award, National Model United Nations - China (2018)
  • Position Paper Award, National Model United Nations - New York (2018)
  • Blanche E. Seaver Faculty-Staff Scholarship, Pepperdine University (2018)
  • Dean’s List, Pepperdine University (2017)

COMMUNITY INVOLVEMENT 🌱

  • Data Science Society, Hertie School (2021-present)
  • Hertie Pride Network, Hertie School (2021-present)
  • Sigma Iota Rho National Honors Society, Pepperdine University (2017-2019)
  • Model United Nations, Pepperdine University (2017-2019)
  • Student Government Representative, Pepperdine University (2016-2017)
  • Step Forward Program, Pepperdine University (2015-2017)

LANGUAGES đź’¬

English Spanish German French
Native B2 B1 B1

Go to the Home Page