Yunfan Ling
New York, NY 571-***-**** ******@********.*** LinkedIn
Education
Work Experience
Data Science Intern — Public Good Consulting LLC (New York, NY)
• Designed and developed a web application based on the framework of an R Shiny dashboard that enables users to explore the details of the 882 high school programs in NYC. The app got more than 500 pageviews and received unanimously positive feedback from the users.
• Used Google Analytics to track website traffic, crafted metrics and conducted product analytics.
Department Research Assistant — Columbia University (New York, NY) 06/2022 — Present
• Performed econometric analysis on South Africa’s four large raw census datasets, 11/2021 — 05/2022 demonstrating empirical evidence of worsened post-apartheid racial segregation.
• Transformed and loaded the datasets, and effectively communicated the segregation patterns to a non-technical anthropologist via data visualization and dashboarding using Python, R Shiny and Tableau.
Research Intern — Rhizome Cultural Consultancy (Shanghai, China) 06/2021 — 08/2021
• Collaborated in four ethnographic research programs on consumers and market landscape, serving client companies including Alibaba and OPPO.
• Researched 20 major international brands from scratch and assessed the marketing outcomes of social media campaigns by creatively applying web scraping to extract user reviews.
• Customized brand strategy and product design for clients by employing ethnographic methods (participant observations, textual analysis, etc.) to acquire cultural insights. Relevant Projects
Winning Space Race with Data Science — Capstone Project for the IBM Data Science Professional Certificate Program, Coursera and IBM 01/2022 — 01/2022
• Obtained SpaceX historical launch records via API and web scraping, performed exploratory data analysis using SQL queries and practiced interactive visual analytics with Python (Folium and Plotly Dash).
• Used various classification models to predict the landing outcome of Falcon 9 first stage with 83% accuracy, and delivered the data-driven insights determining launching cost in a data findings report.
Detect Spams from SMS Messages — Group project for the course “Natural Language Processing”, Columbia University
• Leading a team of four, collaboratively built an ETL pipeline to process text messages with a large corpus of SMS messages.
• Leveraged various ML techniques including ISTM networks and random forest classifier and performed hyperparameter tuning with the scikit-learn and Keras Python library to detect spams, achieving an accuracy of 99%.
11/2021 — 12/2021
Mask Mandates, Economics Activity, and COVID-19 Spread in the United States — Capstone project of “International Policy Action Lab” Program, University of Chicago
• Wrote literature reviews for a working paper covering topics about COVID-19 spread, policy interventions in epidemiology and mask use as a coauthor.
• Assembled the first database of local mask mandates in the US with a team of 50.
• Created choropleth maps illustrating the start dates of regional mask mandates, visualizing COVID-19 cases by state and date using ggplot2. Columbia University — Master of Arts in Quantitative Methods in the Social Sciences with Data Science Focus
GPA: 4.1/4.0; Honor and Awards: Winner of the QMSS/QASR Datathon 09/2021 — Present
09/2017 — 06/2021
The Chinese University of Hong Kong, Shenzhen — Bachelor of Business Administration in Economics
GPA: 3.5/4.0; Honor and Awards: Dean’s List, Bowen Scholarship Skills
• Tools and Technologies: Python (Pandas, NLTK, Scikit-Learn, TensorFlow), R (ggplot2, shiny), SQL (Proficient), Tableau, STATA, Plotly, JavaScript (D3), AWS, HTML, CSS, Figma, C++, MATLAB, Azure, GitHub, Git, Power BI
• Relevant courses: Quantitative Methods for Policy Evaluation, Computer Science, Machine Learning, Deep Learning, Natural Language Processing, UI Design, Time Series, Financial Data Analysis, Econometrics, Data Visualization, Modern Data Structure, IBM Data Science Professional Certificate 07/2020 — 08/2020