Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions

2021/12/21 by Adam Lesnikowski, Lesnikowski, Adam, Gabriel de Souza Pereira Moreira +5
Computer Science · Engineering · #Privacy-Preserving Technologies in Data #Recommender Systems and Techniques #Traffic Prediction and Management Techniques #cs.IR #cs.LG

paper · pdf · doi:10.48550/arxiv.2112.11022

7 pages, included in SimuRec 2021: Workshop on Simulation Methods for Recommender Systems at ACM RecSys 2021, October 2nd, 2021, Amsterdam, NL and online

arxiv created 2021/12/21 · arxiv updated 2021/12/22

Abstract

Synthetic data and simulators have the potential to markedly improve the performance and robustness of recommendation systems. These approaches have already had a beneficial impact in other machine-learning driven fields. We identify and discuss a key trade-off between data fidelity and privacy in the past work on synthetic data and simulators for recommendation systems. For the important use case of predicting algorithm rankings on real data from synthetic data, we provide motivation and current successes versus limitations. Finally we outline a number of exciting future directions for recommendation systems that we believe deserve further attention and work, including mixing real and synthetic data, feedback in dataset generation, robust simulations, and privacy-preserving methods.

Related

• Data Generation via Latent Factor Simulation for Fairness-aware Re-ranking
• Partially Synthetic Data for Recommender Systems: Prediction Performance and Preference Hiding
• Generating Diverse Synthetic Datasets for Evaluation of Real-life Recommender Systems
• Synthetic Data-Based Simulators for Recommender Systems: A Survey
• Doing Data Right: How Lessons Learned Working with Conventional Data should Inform the Future of Synthetic Data for Recommender Systems