Recommendation System Simulations: A Discussion of Two Key Challenges
This work addresses methodological challenges in simulating recommendation systems, which is important for researchers studying their societal impacts, though it appears incremental rather than groundbreaking.
This paper discusses two key challenges in recommendation system simulations: modeling user engagement with recommended items and accounting for non-platform item discovery. It reviews existing simulation assumptions and proposes alternatives while outlining limitations and open questions.
As recommendation systems become increasingly standard for online platforms, simulations provide an avenue for understanding the impacts of these systems on individuals and society. When constructing a recommendation system simulation, there are two key challenges: first, defining a model for users selecting or engaging with recommended items and second, defining a mechanism for users encountering items that are not recommended to the user directly by the platform, such as by a friend sharing specific content. This paper will delve into both of these challenges, reviewing simulation assumptions from existing research and proposing alternative assumptions. We also include a broader discussion of the limitations of simulations and outline of open questions in this area.