Data Science Commons^™

Enhancing The University Of Arkansas' Operations Through Data Science, Aura L. Pinto-Avelar

Data Science Undergraduate Honors Theses

As universities navigate financial constraints and resource allocation challenges, data driven financial analysis has become increasingly important. Universities employ various methods to assess financial efficiency, predict future expenditures, and optimize student credit hour distribution. However, the approaches to financial analysis vary widely, with some institutions leveraging advanced predictive modeling and business intelligence tools, while others rely on traditional budgeting techniques and manual forecasting.

This thesis examines how the University of Arkansas' (“Uark”) financial analysis methods compare to those of other institutions and alternative data-driven approaches. Using four years of financial and student credit hour data, this study evaluates cost trends …

Lucky Charms: Leveraging Consumer Data Analysis For Strategic Decision-Making At General Mills, Katherine Page Thomas

Data Science Undergraduate Honors Theses

This undergraduate thesis examines the application of data analytics in sales strategy and consumer insights from the perspective of a summer internship at General Mills. It gives an overview of the company’s background, industry position, and intern’s role within the sales organization. It outlines the personal learning objectives established before the internship and how they evolved through practical experience.

A central focus of the summer internship was the analysis of consumer demographics within the cereal category to enhance sales performance and optimize retail execution. Using the Data Science Analytics Process as a framework, this thesis details the problem statements, methodologies, …

Optimizing Fire Station Placement In Sugar Land, Tx: A Socioeconomic Risk-Based Approach, Alicia Gallemore

Data Science Undergraduate Honors Theses

Fire station placement has a critical role in emergency response efficiency and community safety. Traditional optimization models focus on mainly the minimization of response times and the maximization of coverage. However, this approach may overlook potential socioeconomic disparities that can influence emergency demand. This study seeks to expand upon the existing project of zoning a fire station in Sugar Land, TX, by integrating spatial road network analysis and publicly available census data—including population density, median household income, and age-based vulnerability—into a Maximal Coverage Location Problem (MCLP) framework. Using a road network-based travel time with realistic constraints, the goal is to …

Attribute Based Assortment Using Machine-Learning, Hector Negron

Data Science Undergraduate Honors Theses

Retail success is influenced by a store's demographic and environmental context, both of which impact item-level sales performance. This study applies machine learning techniques to optimize item allocation based on club attributes at Sam’s Club locations. By analyzing store- specific factors such as proximity to universities, income levels, and regional preferences, the research identifies patterns that contribute to product demand. The results offer insights into how clubs can enhance inventory decisions, improving sales outcomes while reducing inefficiencies. This study reinforces the value of data-driven retail strategies and presents a practical framework for implementing predictive models in a real-world business context.

Shortage To Surge - Studying The Post-Covid-19 Guitar Retail Market, Jed H. Kim

Data Science Undergraduate Honors Theses

The COVID-19 pandemic was one of the most catalyzing events of the 21st century, leading to supply chain disruptions, lifestyle changes, and a massive shift towards digital technologies. During the COVID-19 lockdown, many people had more free time, and over 16 million individuals learned to play guitar in the first 2 years of the pandemic. According to a study by Fender, 62% of these new guitar learners cited the pandemic as their primary reason for learning the instrument. However, pandemic policies and supply chain disruptions meant that many guitar retailers were unable to satisfy demand, and backorders accumulated. After the …

Computer Vision In Soccer: Yolov11 Analytics Engine For Quantifying Game Strategy, Connor S. Maurer

Data Science Undergraduate Honors Theses

Single-shot object detection capabilities significantly reduce computational overhead for real-time computer vision in sports analytics at 60 FPS. YOLO11’s lightweight CNN gives promising accuracy while meeting the low-latency demand of dynamic soccer matches. As data-driven approaches take over the sport of soccer, efficient player tracking systems become critical for informing coach’s strategies. I prototype the ETL (Extract, Transform, Load) process of data collected from a single- shot detection program and evaluate its viability for estimating player fatigue. YOLO11 detects players, the ball, and other characteristics, with the output transformed by homography to estimate the positions in the real world. These …

Reinforcement Learning, Modeling Markets, And Professional Basketball Free Agency, Jacob Cohn

Computational and Data Sciences (PhD) Dissertations

This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.

Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study …

Nutmeg: Separating Signal From Noise In Annotator Disagreement, Jonathan W. Ivey, Susan Gauch, David Jurgens

Data Science Undergraduate Honors Theses

NLP (natural language processing) models often rely on human-labeled data for training and evaluation. Many approaches crowdsource this data from a large number of annotators with varying skills, backgrounds, and motivations, resulting in conflicting annotations. These conflicts have traditionally been resolved by aggregation methods that assume disagreements are errors. Recent work has argued that for many tasks annotators may have genuine disagreements and that variation should be treated as signal rather than noise. However, limited work has combined the two frameworks to separate signal from noise in human-labeled data. In this work, we introduce NUTMEG, a new Bayesian model that …

Application Of Regression Techniques On Designed Economic Data, Naomi O. Edegbe

All Theses

Evaluating stock market data and public companies' performance is an overwhelming task for day traders and brokers in the United States and internationally. As a financial metric of a company's overall valuation, earnings per share is a commonly researched measure of a company's profitability. We investigate relationships between earnings per share, multiple financial measures reported from company income statements, and classifiers such as market capitalization and sector. Multiple linear regression models are developed and assessed for this data. Results conclude that there is a significant difference between sectors and earnings per share recorded for a given company. Individual stock analysis …

Multimodal Benchmarking For Ncaa Basketball, Brendan Barnett

Honors Scholar Theses

We present the first multimodal, multitask benchmark for NCAA basketball, synthesizing structured statistical features with large language model (LLM)-generated game summaries across 19,739 games spanning four NCAA Division I seasons (2021--2025). We evaluate three model families---XGBoost, deep neural networks, and Transformers---under tabular-only and early-fusion settings to measure the impact of LLM-derived textual embeddings. To assess practical utility, we simulate fixed-stake and Kelly criterion-based betting strategies using historical bookmaker odds, analyzing both profitability and downside risk via Monte Carlo simulation. Our results show that XGBoost with early-fusion achieves the highest return on investment and the lowest risk of loss. This work …

Toward Robust Semantic Segmentation In Levee Infrastructure Monitoring: Enhancing Accuracy With High-Fidelity Synthetic Data And Ensemble Learning, Padam Jung Thapa

LSU New Orleans Theses and Dissertations

Abstract: Levees serve as critical flood protection structures, but failures due to inadequate maintenance and extreme water pressures have led to devastating events such as Hurricane Katrina. Manual inspections are slow, labor-intensive, and prone to human error, necessitating the development of automated solutions. This study proposes an AI-driven framework for levee inspection utilizing deep learning-based semantic segmentation to detect rutting and enhance the identification of sand boils. To address dataset limitations, high-fidelity synthetic images are generated using DreamBooth for fine-tuning, while ControlNet adds structural constraints to enhance realism and consistency. A semi-automatic convex hull annotation technique enhances labeling efficiency, and …

Radar Precursors To Severe Weather Reports In Left-Moving Supercells, Eric A. Carothers

Department of Earth and Atmospheric Sciences: Dissertations, Theses, and Student Research

While much research has examined dual-polarimetric signatures of right-moving supercells, very little has been done with left-moving supercells. Given that left-moving supercells are thought to be disproportionate producers of large hail, understanding their internal dynamics is vitally important. This study examines differences and trends in the dual-polarimetric signatures of left-moving supercells to identify precursors to severe weather reports. A dataset of left-moving supercells associated with severe weather reports was created. These storms are processed with an automated analysis algorithm that identifies and quantifies the polarimetric signatures in each storm. A method for analysis of differences and trends in their dual-polarization …

Maximal Independent Set Algorithms Within Procedural Planar Maps: A Large-Scale Evaluation, Chaucer Ihrig

Honors College Theses

Analysis of a childhood game has led us to the problem of maximum independent sets in planar graphs. We wrote a graph creation utility using R to generate a random planar map and its dual graph. This utility then finds a graph’s maximal independent set using a variety of six algorithms. We investigate statistical connections between graph structure, colorability, and the maximal independent sets found using these algorithms over an incredibly large and procedurally generated dataset. We find one can always win the coloring game if the resultant graph is two-colorable. The algorithms perform statistically and practically significantly better on …

Ml Playground: Data Modification/Preprocessing And Model Simulation Tool, Marco D. Cerrato

Electronic Theses, Projects, and Dissertations

There is a heavy reliance on programming when it comes to learning machine learning (ML). This often creates barriers for students and newcomers unfamiliar with coding. While the lessons you learn in the classroom provide essential foundational understanding, some technical or practical aspects of ML—such as data preprocessing, feature engineering, and model tuning—are best learned through hands-on interaction. ML Playground was developed to act as a proof-of-concept application to address this gap by offering a browser-based, graphical user interface that lets users engage with core ML workflows without writing code. Designed with educational accessibility in mind, the application allows users …

Icylib: A Scalable Solution For Reproducible Image Classification Workflows, Leo Williams

Data Science Undergraduate Honors Theses

With the rapid expansion of e-commerce over time, ensuring the diversity and quality of product images has become a critical challenge infeasible for human completion. In conjunction with Walmart Global Tech for the Team 1 Data Science Practicum Project, image classification models were trained to assess product image sets, but training and deploying such models often involves repetitive code and inefficient processes. This thesis presents a reusable modeling library, named IcyLib, designed to streamline the training, validation, and testing of image classification models as well as dataset importation using PyTorch. IcyLib provides a structured yet flexible approach for model implementation, …

Extending Simulation-Enhanced Bayesian Optimization Of System Designs: A Computational Study, Luke Kim

Data Science Undergraduate Honors Theses

This honors thesis builds off work initially accepted for publication in the Proceedings of the 2025 IISE Annual Conference & Expo, which introduced “Simulation-Enhanced Bayesian Optimization” (SEBO)—a hybrid testing optimization approach that combined the usage of unbiased but costly physical experiments with the usage of cheaper but potentially biased computer experiments to optimize engineered systems. The original study established the SEBO methodology and demonstrated its effectiveness on a multimodal, two-dimensional benchmark function. Expanding on the work performed, we conduct a broader evaluation of the SEBO framework through parameter testing and experimentation under a variety of additional benchmark functions. This investigation …

Enhancing Product Image Classification: Utilizing Machine Learning Models For Retail Applications, Avery A. Thompson

Data Science Undergraduate Honors Theses

The expansion of e-commerce has continued at a blinding pace since the COVID-19 pandemic, and retailers are constantly looking for new ways to retain customers. Ensuring that diverse and well-classified images are on product pages has been a paramount method for retailers to ensure retention as they increase product engagement and sales and enhance user experience. Managing and labeling these vast catalogs of images by hand is becoming increasingly infeasible, so some online retailers have started to turn to automated classification models to assist them. Accuracy in these classification models is integral, as a good image classification model can improve …

A Machine Learning Analysis Of Factors Leading To Major League Baseball Postseason Berths, Chase S. Foster

Undergraduate Honors Theses

Machine learning is a method that employs statistical algorithms to identify patterns and make predictions from data. This study applies machine learning techniques to analyze data from Major League Baseball (MLB) teams between 1998 and 2024, with the goal of determining which factors strongly influence a team's likelihood of reaching the postseason and in accurately predicting the teams that do and do not qualify for the postseason. Data exploration and unsupervised machine learning methods such as clustering were used to identify underlying patterns in team performance metrics and determine potential significant contributors to team success. Many different supervised learning methods …

Describing Functionality In Natural Language May Improve Decomposition Behaviors, Matthew R. Burns

All Graduate Theses and Dissertations, Fall 2023 to Present

Problem decomposition—the ability to break complex problems into simpler parts—is a critical skill for computer programming that many beginning students struggle to develop. This research examines how using natural language to describe program functionality can help students develop better problem-solving approaches.

We created a tool called ”Natural Language Functions” (NLFs) that allows students to write descriptions of what they want their code to do in plain English, which then generates working Python functions. We studied how students used this tool compared to students who solved programming problems in traditional ways.

Our findings show that students who used the NLFs tool …

Explainable Ai (Xai) For A Machine Learning Heart Disease Prediction Model, Sai Abhishek Sanchula

Electronic Theses, Projects, and Dissertations

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes & Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg & Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis …