Addressing Fairness and Bias in Machine Learning for Adaptive Video Streaming: Strategies for Enhancing User Experience and Mitigating Algorithmic Discrimination

As adaptive video streaming becomes integral to content delivery in diverse user environments, the role of machine learning in optimizing streaming algorithms raises critical concerns about fairness and bias. This review paper examines the intersection of machine learning and adaptive streaming, focusing on potential biases in models and their implications on content delivery. We explore the challenges associated with achieving fairness, considering user preferences and demographics. By analyzing case studies and existing literature, we identify biases in adaptive streaming models and propose strategies to ensure fairness. The paper emphasizes the importance of transparency, accountability, and user-centric considerations in the design of machine learning algorithms for adaptive streaming. Insights from this review aim to guide researchers, practitioners, and industry stakeholders in developing more equitable and user-friendly adaptive streaming solutions.