I am a recent graduate of the statistics program at Brigham Young University (Aug 2020-Jun 2023), where I specialized in data science. I am passio 61BF nate about using data to drive insights, create models, and inform business decisions.
- Data Analysis: I am skilled in performing complex analyses in R, including spatial, longitudinal, and time-series analyses, as well many other similar analyses in python's libraries.
- Machine Learning: I am proficient in Python's sklearn library to implement various machine learning techniques such as classification, regression, clustering, and neural networds.
- Data Visualization: I am proficient in creating visualizations and communicating insights through ggplot, matplotlib, seaborn, Tableau, RShiny, and other tools.
I have experience working on a variety of data science projects, including:
- Customer segementation in sklearn: During my current internship, I have had the opportunity to head a clustering analysis aimed at segementing the business's customers into distinct personas based on a personality survey they had published. After extensive data cleaning, I used dimensionality reduction to visualize the data, found data discrepancies in certain markets, fit initial clustering algorithms, and created an RShiny app to more easily display the distribution of answers to various questions by cluster. This project is still in progress and I hope to add more to this description as I continue to uncover more insights!
- App conversion rate and purchases report: At my internship, I also worked with the company's databases in dBeaver to pull a report on their app's customer conversion rate on a market and affiliate level. Working with more senior members of the team, I wrote complex SQL queries to extract the necessary information.
-
Predictive modeling for house prices: Using Python, I developed a machine learning model to predict house prices using this Kaggle dataset, achieving an
$R^2$ of 94.5% and winning top place in my class for the best model. - Longitudinal study of PM exposure in children inside the house: Using R, I analyzed data from a longitudinal study of children's exposure to particulate matter and found that the tradition method of stationary PM measurements is insufficient for capturing the true exposure and that the type of activity is effects the amount of PM exposure depending on the child.