In this project, we have proposed a model to formalize multistakeholder fairness in recommender systems as a two stage social choice problem. We express recommendation fairness as a novel combination of an allocation and an aggregation problem, which integrate both fairness concerns and personalized recommendation provisions, and derive new recommendation techniques based on this formulation. This approach allows us to consider fairness in real-world application settings as much more complex and multifaceted compared to a classification problem. We are currently running simulations to demonstrate the ability of the framework to integrate multiple fairness concerns in a dynamic way. These simulations include a combination of different data sets, real and synthetically generated data, different allocation mechanisms, and different social choice rules.

Next Post Previous Post