Machine learning models are increasingly used for high-stake applications that can greatly impact people’s lives. Despite their use, these models have the potential to be biased towards certain social groups on the basis of race, gender, or ethnicity.

Despite an awareness of the need for these fair models, there still exist various technical challenges in the field of algorithmic fairness. In most situations, a significant bottleneck is that more than one fairness measure cannot be satisfied. Therefore, we need to develop a multi-objective fairness pipeline that can balance both group and individual fairness. This project proposes the utilization of a combination of existing debiasing techniques to satisfy both a group and individual fairness metric.

I am participating in SuperUROP because I am passionate about fairness in the machine learning space and believe research is key to driving more equitable technology. Although I did not come from a research background, previous UROPs and project-based classes, have prepared me for an end-to-end research pipeline. Ultimately, with my project, I am excited to show breadth and depth of the responsible AI field.