Business Analytics Commons^™

Mortgage Default Classification Modeling For Variable Analysis, Brendan R. Goggins

Honors College Theses

The financial crisis of the early 2000’s is a prime example of the severe consequences that mortgage default and borrower insolvency can have on economies at large. Mortgage default specifically is a prime case with the popularization of mortgage backed securities and the commonality of this loan structure. Multiple hypotheses and models have been formed to understand the reasons, causes, and consequences of mortgage default. This paper uses both machine learning and statistical classification models to inform an understanding of the variables most significant and impactful to the default outcome of mortgages. Consideration is given to both loan-level microeconomic variables …

Kennesaw State University Student Managed Investment Fund Sector Sensitivity Analysis, John Kiersznowski, Joe Johnson, Kyler Howell, Geranger Lewis

Senior Design Project For Engineers

The Kennesaw State University Student Managed Investment Fund (SMIF) Sector Sensitivity Analysis focuses on improving the fund’s decision-making and performance through data science. The SMIF is a diversified index fund designed to outperform indices like the S&P 500. This project investigates how macroeconomic variables—such as GDP growth, inflation, interest rates, and commodity prices—impact sector performance. By structuring data, developing a sustainable data pipeline, and leveraging advanced statistical techniques and predictive modeling, our team was able to provide the framework and proof of actionable insights that enhance the fund's ability to manage risks and optimize returns.

Measuring Exposure Through Targeted Ads, Sarah Bazell

Honors Projects

This study investigates the effectiveness of targeted digital advertising strategies for Company X, a performance motorsports fuel brand. With the goal of optimizing engagement and improving budget allocation, four distinct ad campaigns were developed and tested on Facebook and Instagram: brand awareness, product education, dealer locator promotion, and lifestyle merchandise promotion. Each campaign was evaluated based on reach, impressions, cost per result, and conversion rates. Descriptive statistics revealed significant differences in engagement rates across campaigns, with video-based, emotionally driven ads outperforming static formats. A one-way ANOVA indicated no significant difference in reach across campaigns but confirmed significant differences in spending …

Ai Meets Economics: Can Deep Learning Surpass Machine Learning And Traditional Statistical Models In Inflation Time Series Forecasting?, Ezekiel N.N. Nortey, Edmund F. Agyemang, Enoch Sakyi-Yeboah, Obu-Amoah Ampomah, Louis Agyekum

School of Mathematical & Statistical Sciences Faculty Publications

This study examined the forecasting ability of deep learning (DL) and machine learning (ML) models against benchmark traditional statistical models for the monthly inflation rates in the USA. The study compared various DL and ML models like transformers, linear regression, gradient boosting (GB), extreme gradient boosting (XGBoost), and adaptive boosting (AdaBoost) with traditional baseline time-series models like autoregressive integrated moving averages (ARIMA) and exponential smoothing (ETS) with Holt-Winters seasonal method utilizing data sourced from the Federal Reserve Bank of St. Louis. The study consistently showed that all DL and ML models outperformed the traditional approaches. In particular, the Transformer (RMSE …

Effect Of Street-Pricing Deregulation In U.S. Airports On Customer Satisfaction, Thorsten Merkle, Satheesh Seenivasan, Sushanta Das

ICHRIE Research Reports

This study investigates the impact of pricing policies and food and beverage (F&B) strategies on traveler satisfaction in the dynamic airport environment, with a focus on Phoenix airport in comparison with two other (undisclosed) major U.S. airports. Using a mixed-methods approach that integrates unstructured observations and social media analytics, the research provides a comprehensive understanding of passenger behavior, satisfaction, and spending patterns in airside F&B outlets.

Key findings reveal that traveler satisfaction is driven by factors such as service quality, timeliness, perceived value, and emotional engagement, with price sensitivity playing a relatively minor role. Phoenix International Airport exemplifies a successful …

Discovering Prompt Engineering: A Qualitative Study Of Nonexpert Teachers' Interactions With Chatgpt, Katherine Carl, Christopher A. Dignam

Research Days

Discussions of the use of artificial intelligence (AI) have become ubiquitous in research, industry, and education. Prompt engineering has emerged as a valuable skill desired by employers, and students have begun to express interest in learning effective ways of interacting with Generative AI. While much research has been done to formalize and optimize the process of prompt engineering, few studies have investigated the use of AI by nonexperts, including nonexpert teachers. In this study, we use qualitative analysis to characterize the process by which nonexpert teachers engage with and learn from ChatGPT as they engage with it as co-creators to …

Enhancing Animal Shelter Operations With Time Series And Machine Learning, Sakava L. Kiv, Donald L. Anderson, Shivam Negi, Jacquelyn Cheun

SMU Data Science Review

Enhancing animal shelter operations through machine learning involves employing a variety of advanced techniques aimed at increasing efficiency, promoting animal welfare, and optimizing resource allocation. This paper explores predictive analytics for adoption rates using regression models to estimate the likelihood of adoption based on historical data, encompassing variables such as breed, health status, and previous adoption trends. Additionally, classification algorithms are utilized to categorize animals by adoption probability, facilitating better resources and marketing prioritization. Clustering algorithms are employed to group animals according to behavior patterns and/or physical health, enabling tailored medical care and enrichment activities that improve their mental and …

Can Kirana Stores Compete In India's E-Commerce Revolution? Rethinking Traditional Retail In The Digital Age, Anshi Jindal, Ashwarya Kapoor

Management Dynamics

E-commerce has reshaped the global retail landscape bringing both disruptions and opportunities specifically in emerging markets like India. This paper explores the evolution of e-commerce in India and its impact on traditional retail particularly unorganized Kirana stores. By analysing market trends, consumer behaviour and policy implications, the study examines how conventional retailers are adapting to digital transformation. Using Reliance Retail’s JioMart initiative as a case study, it provides insights into the integration of digital and physical retail ecosystems. While e-commerce challenges Kirana stores, it also fosters innovation, growth and the emergence of hybrid retail models.

Data-Driven Default Prediction: Insights From Lending Club, Shumaila Gilani, Viktoria Kleer Kliimand

SPARK Symposium Presentations

Peer-to-peer (P2P) lending has transformed consumer credit markets by providing an alternative to traditional banking institutions. LendingClub, a pioneer in this space, facilitates lending between individual investors and borrowers through a data-driven risk assessment model. Our research aims to enhance loan default prediction by developing a more precise classification model based on LendingClub’s historical loan data, ultimately improving risk assessment for investors.

Utilizing a dataset of approximately 650,000 loans from 2007 to 2015, we construct a predictive model to classify loan default risk. Our approach focuses on key financial indicators, including interest rates, borrower grades, debt-to-income ratio, and delinquency history, …

A Machine-Learning Tool-Supported Methodology For Nonprofit Donor Analysis, Corbin Weiss

Campus Research Month

We developed a machine-learning tool-supported methodology for modeling the nonprofit donor relationship. This approach was demonstrated in the case of a US-based nonprofit. Conclusions were drawn from this example and tool-support provided for use by other nonprofits.

A Comparative Analysis Of Financial Ratios In Healthcare Sectors, Lucille Barnett

Undergraduate Theses

How can for-profit financial strategies be adapted to support nonprofit financial stability? And how would those strategies translate to entities with diverse operational goals? The purpose of this study was to conduct a comparative analysis of nonprofit and for-profit healthcare organizations operating in Texas, examining financial differences driven by organizational structures and objectives across three healthcare sectors: Hospitals, Specialty Care Providers, and Community Health Centers. Using financial data from Form 990 and 10-K tax filings, this analysis aims to identify sector-specific financial challenges and opportunities, providing insight for financial decision-makers seeking to improve the long-term sustainability of nonprofit healthcare providers.

Sustainable Leadership In Family-Owned Businesses: The Practice Of Searching Profitability And Evaluating The Business’ Effects On The Environment, Ahmad Mansour, Hind Al-Ahmed, Ahmad Shajrawi, Khaled Alshaketheep, Muhammad Alshurideh, Arafat Deeb

An-Najah University Journal for Research - B (Humanities)

Objective: This research studies family business sustainability leadership adoption obstacles especially regarding their dual need to achieve both profitability and environmental impact targets while examining potential solutions to these problems. Methodology: A research methodology included literary analysis and field studies along with questionnaire distribution for obtaining qualitative and quantitative data. The research survey gathered information about how family businesses handle sustainability measures that focus specifically on their energy consumption as well as energy efficiency and water management plans. Results/Findings: The analysis revealed renewable energy adoption by 80% of the businesses along with energy efficiency implementation in 75% of the …

Does Ai Help Or Harm? Why And How Ai Use Influences Workplace Outcomes And Employee Well-Being, Haille Trimboli, Reka Lassu

Education Division Scholarship

Although the recent surge in excitement surrounding artificial intelligence (AI) might suggest it is a new development, AI has been applied in organizations for over forty years (Fanti et al., 2022; Markelius et al., 2024). Indeed, the term "artificial intelligence" itself emerged in the 1950s during a research project at Dartmouth College, where it was used to describe "machines able to simulate human intelligence" (Haenlein & Kaplan, 2019, p. 3). Most recently, in 2022, the landscape of AI use for laypeople greatly changed when OpenAI introduced ChatGPT, a generative AI tool, to the public; ChatGPT is an advanced AI language …

Benford's Law And The Impact Of Director Blockholders, Ying "Caroline" Chen

Presentations - 2025

This presentation was given by a faculty member on Benford's Law and it's effects on management.

"Benford's Law is a mathematical law which relates to the leading digits of numbers in naturally occurring tables. The probability of the first digit equaling some number d is roughly equal to

𝑃 𝑑 = 𝑙𝑜𝑔10 (1 + 1 𝑑)

The probability of the second digit equaling some number d is roughly equal to

𝑃 𝑑 = σ𝑥=1 9 𝑙𝑜𝑔10 (1 + 1 10𝑥+𝑑)

Durtschi, Hillison, and Pacini (2004) – Analysis using Benford’s Law is primarily useful on sets composed of mathematical combinations of …

Analyzing Stability Of Estimates At Completion For Long Duration Development Efforts, Bradley Vuu, Jonathan D. Ritschel, Brandon M. Lucas, Edward D. White

Faculty Publications

Defense program managers utilize Earned Value Management (EVM) methodologies to measure, report, and predict the cost and schedule performance of their programs. Previous research conducted by Christensen (1996) and Kim et al. (2019) has shown varied results in the stability of EVM Estimates at Completion (EACs). Stability is defined as a 10% or less deviation from the final EAC at a specified percent completion point of the program. The Christensen (1996) and Kim et al. (2019) studies also noted that program-specific factors, such as phase, can impact the accuracy of EVM metrics. This study builds upon those works by assessing …

Gojo & Company, Inc.: Collaborate To Elevate - Microfinancing Through Strategic Partnerships, Ellenna Divingnzzo, Joshua Feng, Charles Moloney, Brendan Shanks, Emma Wagner

B-Corp Case Studies by UNL Raikes Seniors

Gojo’s mission is to “extend financial inclusion across the globe” with the goal “to enable the provision of high-quality affordable financial services in 50 countries” (Impact Report, Gojo, pg. 4). They are a microfinance institution (MFI) that provides financial assistance mainly to individuals in five countries: Cambodia, Sri Lanka, Myanmar, India, and Tajikistan (Impact Report, Gojo, pg. 10). They also have partnerships that extend into many other countries to a lesser extent. Gojo’s group companies provide services such as group loans, business loans, microenterprise loans, emergency loans, voluntary savings, affordable housing, microcredit depositing, and more to over 2.4 million clients. …

Tillamook: Ethical Values Or Misleading Marketing?, Victoria Chin, Ealynn Hsu, Kyana Le, B Littman, Natalia Trejo Andalon

B-Corp Case Studies by UNL Raikes Seniors

Tillamook began as a humble cooperative for the local dairy farmers of Tillamook County, Oregon, to ensure that high-quality cheese was the local standard. As time passed, Tillamook evolved to establish an internal Farm Services Team to help support each farmer and pay above market value for members’ milk–in return, receiving a stable supply of dairy to manufacture its dairy-based products. Additionally, the farmers are still the ones who call the important shots for Tillamook rather than other corporate shareholders. Tillamook County Creamery Association (TCCA) has since expanded nationally, but the foundation remains the same: high-quality dairy to create high-quality …

Cotopaxi: Stewardship To Succession, Roy Dumblauskas, Landry Geiger, John Post, Jack Smiley, Zachary Wallenburg

B-Corp Case Studies by UNL Raikes Seniors

Cotopaxi is a company built from the ground up to be socially conscious, from their governance structure to their deeply ingrained core values. Despite being in a market dominated by incumbents like Patagonia, they've done well in the past, bringing in around $160 million in revenue in 2023 while donating millions outright and carefully maintaining ethical internal business practices. But just as the company began taking off, founder Davis Smith left the company to pursue religious mission work. He spent years, starting the search in 2019 before finally stepping down in July 2022, looking for a successor, eventually finding a …

Aesop Under L'Oreal: Growth Vs. Brand Integrity, Gowrav Ghatamaneni, Spencer Godina, Reed Mchenry, Cole Miller, Shruti Pradeep

B-Corp Case Studies by UNL Raikes Seniors

Founded in Melbourne, Australia, in 1987, Aesop has emerged as a global luxury skincare brand known for its minimalist packaging, commitment to sustainability, and sensory in-store experience. In 2023, L'Oréal Groupe acquired Aesop from Natura & Co. in a deal valued at $2.5 billion, marking the largest acquisition in L'Oréal's history. The brand's dedication to aesthetics has set it apart in the competitive beauty industry. But how does a brand built on small-scale, curated retail experiences navigate the expansion driven by a multinational owner? Can Aesop maintain its core values while scaling up?

New Belgium Brewing: Balancing Growth And Company Values Post-Acquisition, Brooke Bode, Charlie Brockmeier, Chase Kling, Zach Hammann, Jace Ruth, Jay Selzer

B-Corp Case Studies by UNL Raikes Seniors

New Belgium Brewing was founded in 1991 by Jeff Lebesch and Kim Jordan in Fort Collins, Colorado, famously inspired by a bicycle tour through Belgium, with "environmental stewardship" viewed as a core value from day one (New Belgium Brewing, nd). From its earliest years, New Belgium had set out to prove that a brewery could be a successful business while also being a force for good. The company implemented open-book management and a profit-sharing program that allowed employees as early as 1998 to vote and give up bonuses to invest in a wind-powered brewery in the U.S. (New Belgium Brewing, …

Bombas: Weaving Purpose Into Profit, Bethany Barnwell, Madelyn Craft, Emily Nau, Carina Swanson, Vaughn Thompson

B-Corp Case Studies by UNL Raikes Seniors

Bombas is a leading premium basics brand with a unique focus on socks and philanthropy. Its 'buy one, give one' model, along with a viral appearance on Shark Tank, helped propel the company into the public eye. Since the company’s inception, they have donated over 150 million essential clothing items to people in need. Bombas’s commitment to quality and product innovation has earned it a loyal consumer base. However, its production practices and business model have faced scrutiny, raising questions about whether the company is truly maximizing its impact in giving back

Forecasting Supply Chain Disruptions And Reducing Costs Through Data Science, Kayla Ahrndt

SPARK Symposium Presentations

The timely and cost-effective distribution of antiretroviral (ARV) and HIV laboratory commodities, particularly in over-exploited and low-resource settings, is imperative through effective Supply Chain Management.This project uses a comprehensive supply chain dataset to analyze pricing trends, predict lead times, forecast demand, and optimize costs for ARV and HIV lab shipments across multiple countries. Through data science, we can predict future demand, detect unusual pricing patterns, assess risks of supply chain disruptions, examine how commodity prices fluctuate over time and across regions, identify key factors influencing shipment lead times, and develop predictive models for future demand. Through anomaly detection techniques, we …

Lemonade: Mini-Case Study Report, Grace Boguslawski, Seth Daup, Aditya Jain, Chaitra Pirisingula, Caden Punteney

B-Corp Case Studies by UNL Raikes Seniors

Lemonade disrupts the traditional insurance industry through its innovative use of AI-driven underwriting and claims processing. By leveraging AI to replace traditional brokers, Lemonade positions itself as a technologically advanced and socially responsible alternative in a legacy-driven market. As a certified B-Corp, the company emphasizes its mission-driven approach, notably donating leftover premiums to nonprofit organizations selected by its customers. This case study examines the strategic challenges arising from Lemonade’s position in an evolving AI landscape. It explores how Lemonade can maintain its differentiation while navigating increasing competition, ethical considerations, and the diminishing sustainability of AI as a unique long-term competitive …

Market Structure Evolution In The U.S. Automobile Industry: A Review Of Diversity And Concentration Metrics, P.V. (Sundar) Balakrishnan

AMTP Proceedings 2025

I examine the evolution of market structure in the U.S. automobile industry from 1937 to the present, focusing on the application of both traditional and novel diversity and concentration metrics. I use the Herfindahl-Hirschman Index (HHI), Comprehensive Concentration Index (CCI), and newer metrics from fields such as ecology and genetics to uncover insights into the shifting dynamics of market power, firm turnover, and industry stability. The U.S. automobile industry, characterized by consolidation and technological advancement, provides a unique case study for analyzing long-term market evolution. I contribute to the literature by synthesizing a broad range of diversity metrics and offering …

Transforming Undergraduate Marketing Research: Building An Industry-Driven Research Incubator, Kristy C. Grayson, David Olsen

AMTP Proceedings 2025

This study presents a transformative approach to preparing undergraduate Marketing Research students for the data-driven workforce by creating the Research Incubator Framework (RIF). Drawing on an entrepreneurial philosophy, this adaptable model integrates open-source statistical tools such as Python and Google Colab, collaborative pedagogies, and strategic partnerships with local businesses to create a dynamic and iterative learning environment. Through hands-on projects with real-world datasets, students developed technical proficiency, critical thinking, and actionable problem-solving skills. The incubator emphasized iterative learning, cross-disciplinary collaboration, and alignment with industry standards, offering a scalable and cost-effective solution for modern marketing education. This study contributes empirical evidence …

1 – 1 > 0: Growing The Pie By Reallocating Shelf Space To Small Brands, Jesse Core, Ho Kim

AMTP Proceedings 2025

We examine whether reallocating shelf space to smaller brands enhances total category sales. During a three-month field experiment involving 20 supermarket stores in Arkansas (10 treatment and 10 control stores), we increased shelf facings for smaller brands in treatment stores and reduced facings for larger brands, while maintaining the total shelf space constant. A difference-in-differences analysis reveals that increasing facings for smaller brands significantly boosts total category sales, with an average increase of 960 ounces per week during the intervention. Notably, sales remained elevated by 786 ounces per week after shelf facings reverted to the original level, indicating a persistent …

The Impact Of Artificial Intelligence On Fashion And Retail Efficiency: A Strategic Analysis, Andrew Burnstine, Raouf Ghattas

Faculty and Staff Publications & Presentations

No abstract provided.

Perceptions Of Artificial Intelligence In Healthcare: A Qualitative Study Among Physicians And Nurses In Florida, Aaron Miri

MUSC Theses and Dissertations

This investigation will leverage participant focus group interviews with 32 clinicians (16 nurses / 16 physicians) to study what, if anything, is inhibiting AI adoption across the hospital. Specific physicians will be sourced across the key service lines of primary care, oncology, cardiology, behavioral health, and emergency department medicine, as these tend to be patient volume driven and thus have the maximum amount of potential for positive impact leveraging AI. Nurses in these same departments will be assessed to analyze if there is a similarity or difference between the nursing and physician AI adoption barriers.

Enhancing Interoperability In Geospatial Analytics Systems: Navigating Diverse Standards For Optimal Data Integrity, Justin W. Bennett

Dissertations

In this study, we explore the domain of geospatial analytics, focusing on how different geographic information systems (GIS) and technology solutions can better communicate and maximize interoperability. Central to our study is the impact of this interoperability on data integrity, which is critical for accurate decision-making in domains like urban planning, environmental management, and national security. Accurate decision-making requires modeling ecosystems that are easy to comprehend and are often intricate due to their physical or artificial nature and the diversity of geospatial parameters; therefore, it is essential to gather a comprehensive array of spatial and temporal measurements. We examine the …

Employee Engagement In Corporate Sustainability Initiatives: An Empirical Comparison Of Conventional And Modern Working Environment Practices, Ahmad Mansour, Hind Al-Ahmed, Ahmad Shajrawi, Khaled Alshaketheep, Muhammad Alshurideh, Arafat Deeb

An-Najah University Journal for Research - B (Humanities)

Objective: The study targets the investigation of Employee Engagement differences across Traditional and New work forms in Corporate Social Initiatives together with workplace practices that boost Sustainable Project Engagement. Methodology: The authors used a mixed-methods design approach in their research. A survey with 300 sustainable project personnel either working full-time or part-time collected quantitative data for analysis. Thirty semi-structured interviews comprised both employee and managerial personnel to collect qualitative data. The evaluation of workplace practices like flexibility and autonomy and communication & leadership on employee engagement was conducted through regression analysis. Researchers employed thematic analysis on interview data for the …