As a passionate individual pursuing a major in Mathematics, Computer Science, and a minor in Economics at Tulane University, I am driven to leverage my expertise in the field of data science. My experiences in technology consulting, university research, and assistant teaching, has honed my skills in scrum methodology, analytics, and leadership.
Over two years as a research assistant, I worked in collaborative and technical project environments. This experience helped me land two consulting internships at PwC, where I further developed my business acumen and presentation skills through client projects.
I am confident that my technical skill set, coupled with my commitment to professional growth, positions me for a promising career in data analytics.
Resume
Projects
Predicting Bond Amounts in Orleans Parish Criminal District Court
Project tests the use of machine learning to predict initial bail amounts and uncover demographic influences on these predictions, using data from the Orleans Parish District Criminal Court.
We have compiled a dataset of over 800,000 court records, focusing specifically on 9,800 cases from 2020 to 2022.
Analyzing OPEC Member Crude Oil Production Quotas
Project analyzes OPEC crude oil production quotas and OECD countries crude oil production from 1960 to 2022.
Modeling Coffee Reviews with Ordinary Least Squares
Project studies data from coffeereview.com, which was obtained through web scraping and published on kaggle.com. Result was a linear regression model that predicts individual
ratings for coffee beans.
Mobile Ad Hoc Network Simulation
Application simulates a Mobile Ad Hoc Network of non-stationary clients linked through wireless connections.
Honors Thesis
This thesis developes an efficient method for measuring distances between graphs. Such methods are vital for structuring complex networks like digital road maps.
Specifically, the project assesses the effectiveness of the traversal distance algorithm in machine learning classification.
The aim was to enhance the precision of the k-nearest neighbors (k-NN) model for classifying geometric graphs that are represented as English letters.
Previous studies have utilized various algorithms for similar purposes; however, this thesis hypothesizes that the traversal distance can offer significant computational efficiency.
