Resume
-
University of California, Berkeley August 2019 – May 2023
B.A. Data Science w/ Emphasis in Cognition GPA: 3.33
Relevant coursework: Principles and Techniques of Data Science, Introduction to Machine Learning and Data Analytics, Data Structures, Information Technology and Society, Data Science & Demography, Linear Algebra
-
Spotify | Data Science Intern
June 2022 – August 2022
• Created dataset of over 100M users using SQL to analyze A/B test data and user data for new native ad product
• Worked closely with product management to ensure product performance aligns with value proposition
• Defined thresholds to segment new audience for product, allowing to reach a 12 times larger audience for artists
• Analyzed performance of segments in python, using Chartify to create visualizations
Schiefer Chopshop | Data Science Intern August 2021 – December 2021
• Increased data backed decisions by 50% using dashboards in Domo to present internally and externally to clients
• Working with interdisciplinary media team on presenting findings and introducing insights through story telling
• Analyzing different campaigns, using A/B testing and feature engineering on data to help brands perform
• Researching applications of machine learning algorithms to be applied to creative platforms
• Interning 15+ hours a week while maintaining full-time course load
Lucia’s | Food Runner May 2021 – September 2021
• Worked 20 hours a week as food runner and pizza maker at authentic Italian restaurant
• Successfully managed coordination of food for take-out and dine in, and opening and closing of restaurant
• Managed and balanced the cash register at Farmers’ Markets, calculating and distributing co-workers’ tips
-
Study Abroad Dashboard
Dashboard documenting my travels as I study abroad at the Universidad Carlos III de Madrid
• Combined Apple Health App data and personally connected data to create a dataset representing each day abroad
• Surveyed cities traveled to on certain metrics including walkability and public transport on a 1 – 10 scale
• Successfully found correlations to visualize including the weather and my mood, and the weather and steps taken
• Designed and deployed Tableau dashboard showing charts and photos showing insights on my travel experience
Spotify Genre Predictor
Utilized Genius API and Spotify API to build a model to predict the genre of a song using NLP and feature extraction
• Interacted with APIs to create a custom data set of over 15,000 songs and their corresponding lyrics
• Built a pipeline to clean and process text, using lemmatization and tokenization
• Developed a model using features of a song (e.g., bass and danceability) and topic modeling on lyrics
• Used this model to successfully predict genres of song with an accuracy of over 92 percent
COVID-19 States’ Response Analysis
In-depth report on a diverse sampling of states and their COVID-19 response
• Cleaned public data set with over 600,000 rows on testing rates, testing availability, and number of positive cases
• Analyzed data, exploring KPIs and metrics to find meaningful ways to analyze performance
• Created visualizations using the seaborn data set to compare different indictors in lowering positive case rates
• Composed report showing how geographical location, pop. size, and political party impacted positivity rate
-
Languages and Software: Python, SQL, Java, Numpy, Pandas, Scikit-learn, Matplot, Seaborn, Jupyter, Git, Domo, Tableau
Skills: Data cleaning, data manipulation, feature engineering, machine learning, data engineering, data visualization
Interests: Pizza making, photographic film, indoor plant collecting, exploring music genres, and hiking with dog