You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Our project is part of the Break Through Tech AI Program, where we work in collaboration with Relativity to tackle the issue of bias in AI models. We are developing tools and methodologies to analyze models, uncover inherent biases, and explore strategies to reduce or eliminate these biases.
Analyzed government enrollment data to answer questions such as does an increase of non-white Students indicate an increase in other factors such as homelessness, migrant, low-income, or non-highly capable and which school district/county is in need of more resources?
Cleaned and analyzed Civil Rights Data Collection (CRDC) data to examine school-related referrals and arrests across states. Created normalized metrics (per 100 schools) to compare disciplinary intensity and analyzed the representation of students with disabilities in referrals and arrests, identifying disparities across states.
Cleansed and transformed the MovieLens dataset using Python, including extracting release years from movie titles, normalizing multi-genre classifications, and preparing rating data for analysis. Built an interactive Tableau dashboard to explore average and weighted movie ratings by genre and decade, identify top-rated movies within each decade, and analyze rating distributions while accounting for differences in rating counts.
Cleaned and analyzed a Spotify tracks dataset containing 114K+ songs across 125 genres. Explored relationships between audio features (danceability, energy, valence, instrumentalness, liveness, tempo, and duration) and track popularity. Built an interactive Tableau dashboard to identify strong, weak, and negative correlations, with comparisons between explicit and non-explicit tracks.
Developed an equipment scheduler using React and JSX, powered by a SQL database. Users can select a school and log in via a token sent to their email. Once logged in, they can schedule equipment, bookmark items, and staff can add new equipment. The project emphasizes real-time availability, streamlining the scheduling process for an improved user experience.
Sade Song Searcher is a dynamic webpage utilizing bootstrap to showcase Sade’s discography, featuring an interactive interface for exploring albums, viewing song lyrics, and implementing a search feature for finding songs by partial lyrics, while collaborating on backend data integration for seamless database functionality.
Created a comprehensive travel planning application using Java and Android Studio, integrating Firebase for data storage and enabling users to create travel logs, plan trips, and research destinations. Features includes a search function, journal entry management (CRUD)