A Framework for Sampling Techniques to Mitigate Algorithmic Bias in ML

This project is being undertaken by Maliheh Heidarpour.

Maliheh’s research focuses on developing trustworthy and fair Artificial Intelligence systems by investigating how sampling techniques can reduce unwanted algorithmic bias in ML models. Her work evaluates the impact of different data balancing and preprocessing strategies from her proposed framework on both fairness and performance outcomes. The research combines statistical analysis, machine learning, and responsible AI principles to support the development of more reliable and ethical data-driven systems.

 Maliheh is supervised by Dr Kevin McDaid and Dr Róisín Loughran.

This project is funded through the Technological University Transfer Fund (TUTF) and DkIT.