Data Projects

Although my full resume is available here, this section showcases a selection of side projects.

For each project, I've included a hyperlinked title to view it on the appropriate site and a brief overview.

I hope you enjoy looking through my work and getting a sense of what I'm capable of as an analytics professional.

Enhancing Financial Literacy Prevention: An Investigation of Socioeconomic and Geographic Influences: In this project, I explored the intersection of syndicated data and financial literacy, focusing on the United States. Using the Consumer Complaint Database and 2020 Census data, I created random forest models to predict states and products based on filed financial complaints in an effort to identify areas where financial literacy can be enhanced.

From Rpubs to GitHub: Lessons Learned in Hosting an RMarkdown File: In this LinkedIn article I describe the process of learning as a data professional. I explain my process from finding errors to correcting them and speak to the lessons I learned along the way. This article discusses an error on an Rpubs file of mine that I embarked on a journey to correct.

Mikayla Edwards - Data Detective: In this presentation, I explained to middle schoolers what I do as a business intelligence professional. To help them better understand, I compared the art of business intelligence to a detective and deemed myself a 'Data Detective'. I discuss the process of finding insights, messy vs clean data, benchmarking, and data storytelling.

Credit Card Default Case Study: In this case study I utilized Taiwan credit card data from the UCI Machine Learning Repository to see if any of the dataset's independent variables could be used to predict whether someone would default on their credit card payment. I cleaned the data, created a correlation matrix, and trained and validated a logistic regression model to determine its accuracy and the significance of independent variables on the response variable based on z values.

Oscars and POC Representation: By merging and cleaning datasets with POC representation and Oscars awards won and creating binary columns, I was able to conduct a correlation matrix to see the relationships between race and 5 categories (Best Picture, Best Director, Oscars Best Actor, Oscars Best Actress, People's Choice). I also integrated a Tableau chart formulated using the conjoined dataset.

Black Innovation Census: While working as a Research and Data Fellow with The Center for Black Innovation, I conducted the first-of-its-kind research on Black Innovator Support Organizations (BISO) in the United States. BISOs are Black-led and Black-serving organizations that have a focus on innovation for tech-focused businesses (e.g., startup education, tech enablement, venture investment, etc.). The research concluded with visualizations showcasing information such as the locations of these organizations, the reach of businesses they serve, and the types of educational and or monetary assistance they provide.

Vendor Analysis for the Bill and Melinda Gates Foundation: My team and I conducted a thorough analysis of the Bill and Melinda Gates Foundation by undertaking a SWOT analysis, compiling available data, analyzing the current architecture, and performing a vendor analysis for data lakes, machine learning, and data visualization technologies.

Nicki Minaj Album Analysis: I conducted an album-by-album sentiment analysis of Nicki Minaj's alter-ego, Roman.

My COVID-19 2020 Q2-Q4 Netflix Summary: I created a summary of my 2020 Q2-Q4 Netflix data to showcase some of my Tableau skills. The data used was pulled from my shared family Netflix using an ELT method allowing it to be cleaned and transformed in Tableau.

Mock Survey Participation: This mock survey dashboard showcases participation metrics, click rates, and open rates.