Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation
arXiv:2110.00811
Abstract
Recommender systems research is concerned with many aspects of recommender system behavior and effects than simply its effectiveness, and simulation can be a powerful tool for uncovering these effects. In this brief position paper, I identify specific types of research that simulation is uniquely well-suited to address along with a hierarchy of simulation types.
Contribution to the SimuRec Workshop at RecSys 2021
References in corpus (5)
- Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions
- How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility
- Collaborative Filtering and the Missing at Random Assumption
- RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising
- Synthetic Attribute Data for Evaluating Consumer-side Fairness