SimuRec: Workshop on Synthetic Data and Simulation Methods for Recommender Systems Research

@article{Ekstrand2021SimuRecWO,
  title={SimuRec: Workshop on Synthetic Data and Simulation Methods for Recommender Systems Research},
  author={Michael D. Ekstrand and Allison June-Barlow Chaney and Pablo Castells and Robin D. Burke and David Rohde and Manel Slokom},
  journal={Proceedings of the 15th ACM Conference on Recommender Systems},
  year={2021}
}
There is significant interest lately in using synthetic data and simulation infrastructures for various types of recommender systems research. However, there are not currently any clear best practices around how best to apply these methods. We proposed a workshop to bring together researchers and practitioners interested in simulating recommender systems and their data to discuss the state of the art of such research and the pressing open methodological questions. The workshop resulted in a… 

Synthetic Data-Based Simulators for Recommender Systems: A Survey

A new consistent classification of existing simulators based on their functionality, approbation, and industrial effectiveness is provided and a summary of the simulators found in the research literature is made.

Welfare-Optimized Recommender Systems

A recommender system based on the Random Utility Model is presented, which opens the door to Welfare-Optimized Recommender Systems, couponing, and price optimization.

Pessimistic Decision-Making for Recommender Systems

A general pessimistic reward modelling approach for off-policy learning in recommendation is proposed and validated, and it alleviates a well-known decision making phenomenon known as the Optimiser’s Curse, and draws parallels with existing work on pessimistic policy learning.

Recommendation Fairness: From Static to Dynamic

The recent developments in recommender systems are portrayed and how fairness could be baked into the reinforcement learning techniques for recommendation are discussed and it is argued that in order to make further progress in recommendation fairness, one may want to consider multi-agent optimization, multi-objective optimization, and simulation-based optimization, in the general framework of stochastic games.

Multimodal Conversational Fashion Recommendation with Positive and Negative Natural-Language Feedback

This work investigates the effectiveness of the recent multimodal conversational recommendation models for effectively incorporating the users’ preferences over time from both positively and negatively natural-language oriented feedback corresponding to the visual recommendations and proposes an approach to generate both positive and negative natural- language critiques about the recommendations within an existing user simulator.

Learning to Bid with AuctionGym

Online advertising opportunities are sold through auctions, billions of times every day across the web. Advertisers who participate in those auctions need to decide on a bidding strategy: how much

Assessing the Impact of Music Recommendation Diversity on Listeners: A Longitudinal Study

We present the results of a 12-week longitudinal user study wherein the participants, 110 subjects from Southern Europe, received on a daily basis Electronic Music (EM) diversified recommendations.

References

SHOWING 1-8 OF 8 REFERENCES

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

Empirical Analysis of Attribute-Aware Recommender System Algorithms Using Synthetic Data

A reasonably good overview of the behavior of attribute-aware algorithms can be obtained by using synthetic data compared to results done with real-life datasets, as well as variable synthetic data to observe their behavior as the characteristic of data varies.

Data Masking for Recommender Systems: Prediction Performance and Rating Hiding

The experimental results demonstrate that the relative performance of algorithms, which is the key property that a data science challenge must measure, is comparable between the original data and the data masked with Shuffle-NNN.

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.

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.

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.

Synthetic Attribute Data for Evaluating Consumer-side Fairness

The Frequency-Linked Attribute Generation (FLAG) algorithm is described, and its applicability for assigning synthetic demographic attributes to recommendation data sets is shown.

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.