Physical Sciences and Mathematics Commons^™

Fine-Tuning A 𝑘-Nearest Neighbors Machine Learning Model For The Detection Of Insurance Fraud, Alliyah Stout

Honors Theses

Billions of dollars are lost within insurance companies due to fraud. Large money losses force insurance companies to increase premium costs and/or restrict policies. This negatively affects a company’s loyal customers. Although this is a prevalent problem, companies are not urgently working toward bettering their machine learning algorithms. Underskilled workers paired with inefficient computer algorithms make it difficult to accurately and reliably detect fraud.

The goal of this study is to understand the idea of -Nearest Neighbors ( -NN) and to use this classification technique to accurately detect fraudulent auto insurance claims. Using -NN requires choosing a value and a …

Analysis Of Covid-19 And Vaccine Administration In Mississippi, Megan Sickinger

Honors Theses

In this work, we develop a simple mathematical model to observe the spread of COVID-19 and vaccine administration in Mississippi. Based on the well-known Kermack-McKendrick Susceptible-Infected-Removed epidemiological model, the ASIRD−V model has eight ordinary differential equations that split infected populations and recovered populations into vaccinated and unvaccinated populations. After determining that the system is reliable for real-world applications, we investigate and determine the stability and equilibrium points of this system. The system is found to be disease-free when R0 < 1 and endemic when R0 > 1. We use MATLAB to numerically solve the system and optimize the model’s parameters over four short periods, two with the …

Large Scale Disease Modeling, Walker Mattox

Master's Theses

In this we study large scale disease modeling. After understanding the mechanics behind the SIR disease model in an ODE sense, we will apply this knowledge to model disease spread in more and more increasing advanced cellular automata. Eventually, some of our cellular automata will include long distance travel. From this discrete data, we can then build an SIR model in the PDE sense to display large scale disease spread.