Fairness and Privacy in Machine Learning Algorithms

<p>Roughly 2.5 quintillion bytes of data is generated daily in this digital era. Manual processing of such huge amounts of data to extract useful information is nearly impossible but with the widespread use of machine learning algorithms and their ability to process enormous data in a fast, cost-effective, and scalable way has proven to be a preferred choice to glean useful insights and solve business problems in many domains. With this widespread use of machine learning algorithms there has always been concerns about the ethical issues that may arise from the use of this modern technology. While achieving high accuracies, accomplishing trustable and fair machine learning has been challenging. Maintaining data fairness and privacy is one of the top challenges faced by the industry as organizations employ various machine learning algorithms to automatically make decisions based on trends from previously collected data. Protected group or attribute refers to the group of individuals towards whom the system has some preconceived reservations and hence is discriminatory. Discrimination is the unjustified treatment towards a particular category of people based on their race, age, gender, religion, sexual orientation, or disability. If we use the data with preconceived reservation or inbuilt discrimination towards certain group, then the model trained on such data will also be discriminatory towards these specific individuals.</p>

Name thesis:degree_name

Master of Science in Computer Science (MSCS)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Year dc:date.available

2022

Author dc:creator

• Bhargava, Neha

Contributors dc:contributor

• Dr. Ramazan Aygun
• Dr. Yong Pei
• Dr. Jiho Noh

• Big Data
• GAN
• Fairness
• Adult
• COMPAS
• German Credit
• Discrimination
• Computer Sciences
• Data Science

Repository record dc:identifier

https://digitalcommons.kennesaw.edu/cs_etd/54

OAI identifier oai:identifier

oai:digitalcommons.kennesaw.edu:cs_etd-1058