Recommender systems can strongly influence which information we see online, eg, on
social media, and thus impact our beliefs, decisions, and actions. At the same time, these …

Counterfactual estimators enable the use of existing log data to estimate how some new
target recommendation policy would have performed, if it had been used instead of the …

While recent years have witnessed a rapid growth of research papers on recommender
system (RS), most of the papers focus on inventing machine learning models to better fit …

Rankings are the primary interface through which many online platforms match users to
items (eg news, products, music, video). In these two-sided markets, not only the users draw …

We introduce the concept of expected exposure as the average attention ranked items
receive from users over repeated samples of the same query. Furthermore, we advocate for …

Prior research on exposure fairness in the context of recommender systems has focused
mostly on disparities in the exposure of individual or groups of items to individual users of …

Ranking items by their probability of relevance has long been the goal of conventional
ranking systems. While this maximizes traditional criteria of ranking performance, there is a …

Recommendation systems are popular in many domains. Researchers usually focus on the
effectiveness of recommendation (eg, precision) but neglect the popularity bias that may …

Considering the impact of recommendations on item providers is one of the duties of multi-
sided recommender systems. Item providers are key stakeholders in online platforms, and …

Metrics commonly used to assess group fairness in ranking require the knowledge of group
membership labels (eg, whether a job applicant is male or female). Obtaining accurate …