Navigating the Landscape of Bias in Recommender Systems

As technology continues to advance and shape the way we interact with the world, the role of online recommender systems in our daily lives is becoming increasingly important. However, these systems have introduced a variety of complex issues related to bias and fairness. Bias in recommender systems can take many forms and hide in the shadows of data, machine learning modeling practices, and the applications of such models. In this talk, we will dive deeper into the different types of biases that can occur in recommendation systems, along with their definitions and characteristics. We will then provide a detailed overview of existing approaches to debias these systems and examine their strengths and limitations. Finally, we will also identify some of the open challenges in this area and offer a glimpse into the exciting future directions that are currently being explored. Through a nuanced and thorough examination of the landscape of bias and debias in online recommender systems, we hope to help you better navigate this tricky space and emerge with a deeper understanding of the complexities and opportunities at play.

View the slides for this session