• Corpus ID: 238259985

Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation

  title={Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation},
  author={Michael D. Ekstrand},
My research agenda is particularly concerned with understanding the human biases that affect information retrieval and recommender systems, and quantifying their impact on the system’s operation, individual and social human experience, and our metrics for quantifying operation, behavior, and experience. This agenda requires significant use of simulation for a variety of reasons, most stemming from the need to study counterfactuals. We can train a recommender system and measure its behavior on a… 

Figures from this paper

Simulating Users’ Interactions with Recommender Systems
The potential of simulations in unlocking certain types of analysis that are infeasible by other means are discussed, based on the simulation of users’ choice behaviour when exposed to recommendations.


Fairness is not static: deeper understanding of long term fairness via simulation studies
An extensible open-source software framework for implementing fairness-focused simulation studies and further reproducible research is provided, and it is shown that static or single-step analyses do not give a complete picture of the long-term consequences of an ML-based decision system.
Blockbuster Culture's Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity
This paper examines the effect of recommender systems on the diversity of sales, and shows how basic design choices affect the outcome, and thus managers can choose recommender designs that are more consistent with their sales goals and consumers' preferences.
Should I Follow the Crowd?: A Probabilistic Analysis of the Effectiveness of Popularity in Recommender Systems
A crowdsourced dataset devoid of the usual biases displayed by common publicly available data is built, in which contradictions between the accuracy that would be measured in a common biased offline experimental setting, and the actual accuracy that can be measured with unbiased observations are illustrated.
Estimating Error and Bias in Offline Evaluation Results
It is found that missing data in the rating or observation process causes the evaluation protocol to systematically mis-estimate metric values, and in some cases erroneously determine that a popularity-based recommender outperforms even a perfect personalized recommender.
Fairness and Discrimination in Information Access Systems
This monograph presents a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic.
RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising
RecoGym is introduced, an RL environment for recommendation, which is defined by a model of user traffic patterns on e-commerce and the users response to recommendations on the publisher websites, that could open up an avenue of collaboration between the recommender systems and reinforcement learning communities and lead to better alignment between offline and online performance metrics.
Collaborative Filtering and the Missing at Random Assumption
Experimental results are presented showing that incorporating an explicit model of the missing data mechanism can lead to significant improvements in prediction performance on the random sample of ratings.
Algorithmic Fairness: Choices, Assumptions, and Definitions
It is shown how choices and assumptions made—often implicitly—to justify the use of prediction-based decision-making can raise fairness concerns and a notationally consistent catalog of fairness definitions from the literature is presented.
How algorithmic confounding in recommendation systems increases homogeneity and decreases utility
Using simulations, it is demonstrated how using data confounded in this way homogenizes user behavior without increasing utility.
Comparing recommender systems using synthetic data
In this work, we propose SynRec, a data protection framework that uses data synthesis. The goal is to protect sensitive information in the user-item matrix by replacing the original values with