Vol. 1, Issue 1, Part A (2024)

In recent years, large-scale recommendation systems have become integral to digital platforms such as e-commerce, social media, and content streaming. While these systems have demonstrated remarkable capabilities in personalizing user experiences, concerns about fairness and bias have become increasingly prominent. Traditional fairness metrics often fail to capture complex social realities, especially those affecting users at the intersection of multiple marginalized identities. This review examines the emerging research on assessing fairness in recommendation systems through intersectional metrics. We explore theoretical foundations, algorithmic frameworks, empirical evaluations and ongoing challenges. The paper highlights how intersectionality offers a richer lens for understanding systemic biases in recommendations, ultimately pushing the field toward more equitable and inclusive systems.