Date of Submission
Spring 2022
Academic Program
Computer Science; Mathematics
Project Advisor 1
Robert McGrail
Project Advisor 2
Caitlin Leverson
Abstract/Artist's Statement
Artificial intelligence and machine learning systems are becoming ever more prevalent; at every turn these systems are asked to make decisions that have lasting impacts on peoples’ lives. It is becoming increasingly important that we ensure these systems are making fair and equitable decisions. For decades we have been aware of biased and unfair decision making in many sectors of society. In recent years a growing body of evidence suggests these biases are being captured in data that are then used to build artificial intelligence and machine learning systems, which themselves perpetuate these biases. The question is then, can we detect these biases in the data before it is used to create these systems? In this paper we will be exploring the feasibility and effectiveness of using a technique from topological data analysis to detect unfair bias in a criminal sentencing dataset.
Open Access Agreement
Open Access
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.
Recommended Citation
Tessier, Ansel Steven, "Does Bias Have Shape? An Examination of the Feasibility of Algorithmic Detection of Unfair Bias Using Topological Data Analysis" (2022). Senior Projects Spring 2022. 208.
https://digitalcommons.bard.edu/senproj_s2022/208
This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.