Overview

My research focuses on data-driven algorithm auditing aligned with the Sustainable Development Goals (SDGs) such as poverty alleviation, health and well-being, gender equality, and reducing inequalities. I work with diverse algorithmic approaches, including machine learning, deep learning, and ranking systems, to address inequality, systemic bias, and fairness at individual, group, and intersectional levels. An important aspect of my work involves impact assessment through feedback loops and interventions. Leveraging multimodal data (e.g., network, tabular, and image data) and both real and synthetic datasets, I develop frameworks and applications tackling network inequality, fairness, and societal disparities, with contributions like high-resolution poverty maps and analyses of online visibility in academia. My goal is to advance equitable, impactful AI systems across societal domains.