Currently an Extern @Breaking GamesI turn messy data into meaningful insights. As a Data Science graduate, I leverage analytics to drive impactful business decisions.
Explore my work in Data Analytics where I leverage SQL and database architecture to create insightful dashboards and analytics solutions.
Breaking Games · ✅ Verified by Extern · ⏱️ In progress
Turn six messy CSVs into an analytics database and a Q4 dashboard that drives real business decisions. SQL + Claude.
Automated API requests to Face++ using Python, processing a dataset of 1,000+ facial images and organizing outputs by demographic attributes (age, gender, race/ethnicity). Identified statistically significant disparities in detection accuracy across demographic groups, surfacing systemic bias in the model’s performance. Documented methodology and findings in a technical report on fairness in ML systems, including limitations and recommendations.
I turn messy data into meaningful insights. As a Data Science graduate, I leverage analytics to drive impactful business decisions.
I am a senior at Rutgers University majoring in Data Science, with a keen focus on Data Analytics. My journey has equipped me with the skills to transform complex data into actionable insights, driving informed business decisions.
Externships
SQL & Database Architecture Externship with Breaking Games
Breaking Games
Experience
Deputy Lead – Avionics & Integration
RU Airborne · September 2024 – August 2025
Academic Tutor
JEI Learning Center · December 2022 – May 2023
Education
Rutgers University – New Brunswick
Bachelor of Science in Data Science · Class of 2026
Skills
✅ Verified by Extern · ⏱️ In progress
Turn six messy CSVs into an analytics database and a Q4 dashboard that drives real business decisions. SQL + Claude.
The work converted six raw e-commerce sources into a populated SQLite analytics database and validated access by writing and running SQL queries with Claude. Deliverables included a data inventory, five instant-answer query results (top products, revenue, product count, ad spend, checkout sessions), and a Week 1 playbook documenting ingestion and validation steps.
I produced a populated breaking_games.db file, a data inventory for all six sources, five instant-answer SQL query results, and a Week 1 playbook that documents ingestion and validation steps.
On Day 1 I mapped six raw data sources and loaded the provided SQLite file, then wrote and ran SQL queries with Claude. I produced a data inventory, five instant-answer queries with results (top products, revenue, product count, ad spend, checkout sessions), and a Week 1 playbook document.
Automated API requests to Face++ using Python, processing a dataset of 1,000+ facial images and organizing outputs by demographic attributes (age, gender, race/ethnicity). Identified statistically significant disparities in detection accuracy across demographic groups, surfacing systemic bias in the model’s performance. Documented methodology and findings in a technical report on fairness in ML systems, including limitations and recommendations.
Built and compared decision trees and Naïve Bayes classifiers on a structured animal dataset achieving 80%+ predictive accuracy. Evaluated model performance using confusion matrices and cross-validation and created data visualization to communicate model performance to non-technical users.