Optimizing an ETL Pipeline From Multiple Angles; The Role of Ethical Design in Building Trust in Machine Learning Algorithms

Author:
Choksi, Akshay, School of Engineering and Applied Science, University of Virginia
Advisors:
Seabrook, Bryn, EN-Engineering and Society, University of Virginia
Foley, Rider, Engineering and Society, University of Virginia
Vrugtman, Rosanne, EN-Comp Science Dept, University of Virginia
Abstract:

My Capstone project's technical enhancements directly contribute to improving data accuracy, reliability, and real-time access for stakeholders within the bank. Simultaneously, my STS project's focus on ethical design principles ensures that these technological advancements are implemented in a manner that respects user privacy, promotes fairness in algorithmic decision-making, and fosters transparency in data handling practices. As a result, this portfolio provides methodology and research for both projects that contribute value to the machine learning (ML) industry. By integrating technical improvements with ethical considerations, the collective impact of these projects not only optimizes operations but also reinforces the bank's commitment to responsible and trustworthy data-driven strategies. Therefore, this STS Thesis builds a stronger foundation for leveraging advanced technologies, like machine learning, effectively, and promotes harmony between producers and end-users.

Degree:
BS (Bachelor of Science)
Keywords:
Ethical Design, Data Pipeline, Machine Learning, SCOT, AWS
Notes:

School of Engineering and Applied Science

Bachelor of Science in Computer Science

Technical Advisor: Rosanne Vrugtman

STS Advisors: Rider Foley, Bryn Seabrook

Language:
English
Issued Date:
2024/05/07