I'm a junior at the University of California at Berkeley studying data science. My passion for data science was fostered heavily by Kaggle, where I've participated in several competitions and explored endless datasets. Scroll down to learn more about the work and projects I've done, as well as the organizations I've been involved in throughout school.
B.A. Statistics • September 2015 - June 2019
Relevant Coursework: Reproducible and Collaborative Statistical Data Science • Principles and Techniques of Data Science • Concepts of Statistics • Data Structures and Algorithms • Foundations of Data Science • Probablility for Data Science • Linear Algebra
Data Science Intern • June 2017 - August 2017
work in progress to be updated.
Kaggle • Python, XGBoost, Pandas
Built a machine learning model to classify the gender of a voice based on sound data. Achieved 98.23% on a 5-fold cross validation metric using a gradient boosting decision tree, implemented with sklearn.
Kaggle • Python, TensorFlow, Pandas
Processed files from a Kaggle dataset containing images of dogs and cats, and built a convolution Nueral Net to achieve 80% classification accuracy.
Team Member • Spring 2017 - Present
I am a member of the curriculum team within the Berkeley Institute for Data Science, working with both professors and students within Boalt Law School to create a curriculum for it's pilot data science class. This involves finding and formatting relevant datasets, and creating lesson plans revolving around applying data science to the field of Law.
Languages: Proficient in Python and Java. Experienced with SQL.
Libraries: Proficient with sci-kit learn, pandas, xgboost, and numpy.