@inproceedings{e4e7ef06fadc4d3f89f295e006386aec,
title = "Data masking for recommender systems: Prediction performance and rating hiding",
abstract = "Data science challenges allow companies, and other data holders, to collaborate with the wider research community. In the area of recommender systems, the potential of such challenges to move forward the state of the art is limited due to concerns about releasing user interaction data. This paper investigates the potential of privacy-preserving data publishing for supporting recommender system challenges. We propose a data masking algorithm, Shuffle-NNN, with two steps: Neighborhood selection and value swapping. Neighborhood selection preserves valuable item similarity information. The data shuffling technique hides (i.e., changes) ratings of users for individual items. Our 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.",
keywords = "Data masking, Privacy-preserving data publishing, Recommender systems",
author = "Manel Slokom and Martha Larson and Alan Hanjalic",
year = "2019",
language = "English",
series = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",
pages = "21--25",
editor = "{Tkalcic }, {Marko } and Sole Pera",
booktitle = "ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results",
note = "2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019 ; Conference date: 16-09-2019 Through 20-09-2019",
}