Standard

Data masking for recommender systems : Prediction performance and rating hiding. / Slokom, Manel; Larson, Martha; Hanjalic, Alan.

ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results: Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). ed. / Marko Tkalcic ; Sole Pera. CEUR-WS.org, 2019. p. 21-25 (CEUR Workshop Proceedings; Vol. 2431).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Slokom, M, Larson, M & Hanjalic, A 2019, Data masking for recommender systems: Prediction performance and rating hiding. in M Tkalcic & S Pera (eds), ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results: Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). CEUR Workshop Proceedings, vol. 2431, CEUR-WS.org, pp. 21-25, 2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019, Copenhagen, Denmark, 16/09/19.

APA

Slokom, M., Larson, M., & Hanjalic, A. (2019). Data masking for recommender systems: Prediction performance and rating hiding. In M. Tkalcic , & S. Pera (Eds.), ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results: Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019) (pp. 21-25). (CEUR Workshop Proceedings; Vol. 2431). CEUR-WS.org.

Vancouver

Slokom M, Larson M, Hanjalic A. Data masking for recommender systems: Prediction performance and rating hiding. In Tkalcic M, Pera S, editors, ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results: Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). CEUR-WS.org. 2019. p. 21-25. (CEUR Workshop Proceedings).

Author

Slokom, Manel ; Larson, Martha ; Hanjalic, Alan. / Data masking for recommender systems : Prediction performance and rating hiding. ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results: Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). editor / Marko Tkalcic ; Sole Pera. CEUR-WS.org, 2019. pp. 21-25 (CEUR Workshop Proceedings).

BibTeX

@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.org",
pages = "21--25",
editor = "{Tkalcic }, {Marko } and Sole Pera",
booktitle = "ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results",

}

RIS

TY - GEN

T1 - Data masking for recommender systems

T2 - Prediction performance and rating hiding

AU - Slokom, Manel

AU - Larson, Martha

AU - Hanjalic, Alan

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Data masking

KW - Privacy-preserving data publishing

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=85071768056&partnerID=8YFLogxK

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

SP - 21

EP - 25

BT - ACM RecSys LBR 2019 ACM RecSys 2019 Late-breaking Results

A2 - Tkalcic , Marko

A2 - Pera, Sole

PB - CEUR-WS.org

ER -

ID: 68758901