Matching Items (254)
Description
The evolution of digital commerce has fundamentally reshaped the landscape of global
financial transactions, establishing an ecosystem where speed, operational efficiency, and user convenience are the highest priority. This transformation, driven by the adoption of
internet-based platforms and mobile technologies, has enabled unprecedented levels of
accessibility and connectivity in economic exchanges. However, this rapid expansion has caused a significant escalation in payment fraud, which exploits vulnerabilities inherent in contemporary transaction systems. Historically, platforms such as Stripe Radar have adopted a centralized approach to fraud prevention, aggregating extensive datasets—including credit card details, behavioral analytics, and device fingerprints—to identify and mitigate fraudulent activities. This methodology, while effective in certain contexts, introduces substantial risks due to the concentration of sensitive information within a single architectural framework. Such
centralization renders these systems prime targets for cyberattacks, as evidenced by high-profile breaches that have compromised millions of users’ personal and financial data.
ContributorsGundala, Revanth (Author) / Boscovic, Dragan (Thesis director) / Bazzi, Rida (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Economics Program in CLAS (Contributor)
Created2025-05
Description
Barrett, The Honors College at Arizona State University supports high‐achieving engineering undergraduates but faces high attrition rates: over 42 percent of engineering students who matriculated between Fall 2015 and the most recent term have formally withdrawn. This study develops a predictive framework to identify students at risk of withdrawal using a cleaned administrative dataset of 5,427 student‐term records and 79 initial features. After rigorous preprocessing—including removal of low‐variance, outcome‐leaking, time‐dependent, and highly correlated variables—we engineered smoothed target encodings and interaction terms, and selected a parsimonious set of predictors observable by the end of a student’s second year. We compared a Decision Tree baseline with a Random Forest classifier, tuning hyperparameters via grid search and 5‐fold cross‐validation. The Random Forest model achieved 76 percent accuracy on a held‐out test set and a mean F1 score of 0.787, outperforming the Decision Tree. Key drivers of withdrawal risk included second‐year cumulative GPA, major‐specific encoding, and the interaction between honors course performance and major choice. These findings offer a foundation for an early‐warning system to guide targeted retention interventions and support timely academic advising.
ContributorsPark, Sungmin (Author) / Menees, Jodi (Thesis director) / Srinivasan, Aravind (Committee member) / Barrett, The Honors College (Contributor) / Economics Program in CLAS (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2025-05
Description
Coal mined from Appalachia was a key contributor to our nation’s success beginning with the Industrial Revolution. However, in modern times Appalachia is nearly as synonymous with environmental degradation and poverty as it is with coal, raising critical questions about the long-term effects of the way extractive industries affect the regions they operate in. This study (a) explores the history of the Appalachian region, the effects of legislative policy, and the ways broader perceptions of miners have evolved in order to examine the way the coal mining industry has affected the health, economic status, and social status of the people dependent on it; and (b) extrapolates these lessons to Arizona’s copper industry. As the demand for copper grows, Arizona’s copper mining grows along with it, and it is essential that patterns of neglect to long-term sustainability for miners and their families not be repeated. To create a resilient mining economy that balances national resource needs and company profits with the health, safety, finances, and social role of the blue collar workers that allow the industry to function there are a number of changes that need to be made. This study finds that improved health and safety standards, requirements for better benefits for disabled employees, a greater level of economic involvement through financial literacy education programs, retraining programs and relocation benefits for laid off employees, and a shift in the way legislators discuss issues surrounding mining and miners are all hugely important for maintaining the sustainability of these communities.
ContributorsSherman, Nora (Author) / Semken, Steven (Thesis director) / Burt, Donald (Committee member) / Barrett, The Honors College (Contributor) / School of Earth and Space Exploration (Contributor) / Economics Program in CLAS (Contributor)
Created2025-05
Description
Given the importance of affordable housing, it is important to study the economic factors that influence it, both on a national and a local scale. In recent years, housing affordability metrics have reported worrying trends, further driving the importance of theoretical research and empirical data that supports it. This paper examined several hypotheses related to housing affordability and federal interest rates. High federal interest rates have long been deemed a cause of worsening housing affordability. Federal interest rates influence mortgage rates, which in turn influence mortgage prices. However, current theory is divided as to the aggregate impact of lowered interest rates on housing affordability. Some suggest that this is overall positive, while others point out that demand effects induced by lower mortgage prices may crowd-out struggling families and worsen affordability. This paper tests current literature regarding the aggregate impact of interest rates on housing affordability as well as exploring the possibility of varying impacts at the local level. Using econometric modeling, this analysis was not able to find any statistically significant correlation between interest rates and housing affordability outcomes at the local level, and there appeared to be no interaction between owner-occupancy rates (a local characteristic) and the effect of interest rates on a community. However, at a national scale, lower interest rates were associated with lower mortgage costs and increasing housing affordability outcomes, suggesting that recent doubts may not stand on solid footing.
ContributorsRounds, Luke (Author) / Thomson, Henry (Thesis director) / Cordova, Luis (Committee member) / Barrett, The Honors College (Contributor) / WPC Graduate Programs (Contributor) / Economics Program in CLAS (Contributor)
Created2025-05