Completed Projects
Customer Classification with K-Means Clustering and CART Modeling
This is a data analysis project examining open-source customer purchasing data from UC Irving’s Machine Learning Repository. It successfully analyzed the data producing both actionable insights on optimal business strategies and a model for classifying customers according to their value to the business.
Read the project report here:
Mock Project Proposal
This is a project management exercise to produce a complete project proposal for a fictional business problem. It sets out to propose a project to implement a digital point of sale system, produce an updated business website with online sale capabilities, and increase advertising efforts through a robust social media presence. The proposal establishes the scope, budget, timeline, and expectations of the project along with the logistics of its execution.
Read the proposal here:
Bring the Center to the Library: A Community Writing Center for Oklahoma
This is a research project funded by the Undergraduate Research and Creative Activity (UReCA) Summer Fellowship. University students often have access to a University Writing Center (WC) which provides free writing consultations and tutoring. This has shown to greatly increase the writing skills of university students. Bring the Center to The Library set out to mirror the pedagogical approaches of a university WC in the context of a public library. Through this project I provided free writing tutoring to the Norman Oklahoma community.
Read the grant proposal here:
Read the results brief here:
In Progress Projects
How public libraries support literacy: predicting literacy rate based on public library metrics.
This is a data analysis project examining the question: Do public libraries positively influence a communities literacy rate? It uses the Public Library Survey, a population level survey of public libraries in the U.S. and U.S. territories, and a measure of public literacy such as the National Assessment of Adult Literacy, a study on the use of written information for adequate function in various life domains. These data sources will be jointly used to determine if communities with higher quantities of public libraries, or better funded libraries, have notably higher literacy rates. Contingent on the finding of a positive relationship, the project will further attempt to produce a model which predicts a communities literacy based on the metrics of its libraries. This model could then be applied for decision making such as optimizing a libraries funding.