Utility aware clustering for publishing transactional data

Michael Bewong; Jixue Liu; Lin Liu; Jiuyong Li

doi:10.1007/978-3-319-57529-2_38

Utility aware clustering for publishing transactional data

Michael Bewong, Jixue Liu, Lin Liu, Jiuyong Li

University of South Australia

Research output: Book chapter/Published conference paper › Conference paper › peer-review

7 Citations (Scopus)

Abstract

This work aims to maximise the utility of published data for the partition-based anonymisation of transactional data. We make an observation that, by optimising the clustering i.e. horizontal partitioning, the utility of published data can significantly be improved without affecting the privacy guarantees. We present a new clustering method with a specially designed distance function that considers the effect of sensitive terms in the privacy goal as part of the clustering process. In this way, when the clustering minimises the total intra-cluster distances of the partition, the utility loss is also minimised. We present two algorithms DocClust and DetK for clustering transactions and determining the best number of clusters respectively.

Original language	English
Title of host publication	Advances in Knowledge Discovery and Data Mining
Subtitle of host publication	21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II
Editors	Jinho Kim, Kyuseok Shim, Longbing Cao, Jae-Gil Lee, Xuemin Lin, Yang-Sae Moon
Place of Publication	Cham
Publisher	Springer International Publishing AG
Pages	481-494
Number of pages	14
ISBN (Electronic)	9783319575292
ISBN (Print)	9783319575285
DOIs	https://doi.org/10.1007/978-3-319-57529-2_38
Publication status	Published - 2017
Event	The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017) - Seogwipo KAL Hotel , Jeju, Korea, Republic of Duration: 23 May 2017 → 26 May 2017 http://pakdd2017.snu.ac.kr/

Conference

Conference	The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017)
Country/Territory	Korea, Republic of
City	Jeju
Period	23/05/17 → 26/05/17
Internet address	http://pakdd2017.snu.ac.kr/

Access to Document

10.1007/978-3-319-57529-2_38

Cite this

Bewong, M., Liu, J., Liu, L., & Li, J. (2017). Utility aware clustering for publishing transactional data. In J. Kim, K. Shim, L. Cao, J.-G. Lee, X. Lin, & Y.-S. Moon (Eds.), Advances in Knowledge Discovery and Data Mining: 21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II (pp. 481-494). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-57529-2_38

Bewong, Michael ; Liu, Jixue ; Liu, Lin et al. / Utility aware clustering for publishing transactional data. Advances in Knowledge Discovery and Data Mining: 21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II. editor / Jinho Kim ; Kyuseok Shim ; Longbing Cao ; Jae-Gil Lee ; Xuemin Lin ; Yang-Sae Moon. Cham : Springer International Publishing AG, 2017. pp. 481-494

@inproceedings{e462d112de4f4f3883dc0f33094447e2,

title = "Utility aware clustering for publishing transactional data",

abstract = "This work aims to maximise the utility of published data for the partition-based anonymisation of transactional data. We make an observation that, by optimising the clustering i.e. horizontal partitioning, the utility of published data can significantly be improved without affecting the privacy guarantees. We present a new clustering method with a specially designed distance function that considers the effect of sensitive terms in the privacy goal as part of the clustering process. In this way, when the clustering minimises the total intra-cluster distances of the partition, the utility loss is also minimised. We present two algorithms DocClust and DetK for clustering transactions and determining the best number of clusters respectively.",

keywords = "Total distance, Utility loss, Privacy model, Term pair, Small cluster size",

author = "Michael Bewong and Jixue Liu and Lin Liu and Jiuyong Li",

year = "2017",

doi = "10.1007/978-3-319-57529-2_38",

language = "English",

isbn = "9783319575285 ",

pages = "481--494",

editor = "Jinho Kim and Kyuseok Shim and Longbing Cao and Jae-Gil Lee and Xuemin Lin and Yang-Sae Moon",

booktitle = "Advances in Knowledge Discovery and Data Mining",

publisher = "Springer International Publishing AG",

address = "Switzerland",

note = "The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017) ; Conference date: 23-05-2017 Through 26-05-2017",

url = "http://pakdd2017.snu.ac.kr/",

}

Bewong, M, Liu, J, Liu, L & Li, J 2017, Utility aware clustering for publishing transactional data. in J Kim, K Shim, L Cao, J-G Lee, X Lin & Y-S Moon (eds), Advances in Knowledge Discovery and Data Mining: 21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II. Springer International Publishing AG, Cham, pp. 481-494, The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017), Jeju, Korea, Republic of, 23/05/17. https://doi.org/10.1007/978-3-319-57529-2_38

Utility aware clustering for publishing transactional data. / Bewong, Michael; Liu, Jixue; Liu, Lin et al.
Advances in Knowledge Discovery and Data Mining: 21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II. ed. / Jinho Kim; Kyuseok Shim; Longbing Cao; Jae-Gil Lee; Xuemin Lin; Yang-Sae Moon. Cham: Springer International Publishing AG, 2017. p. 481-494.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Utility aware clustering for publishing transactional data

AU - Bewong, Michael

AU - Liu, Jixue

AU - Liu, Lin

AU - Li, Jiuyong

PY - 2017

Y1 - 2017

N2 - This work aims to maximise the utility of published data for the partition-based anonymisation of transactional data. We make an observation that, by optimising the clustering i.e. horizontal partitioning, the utility of published data can significantly be improved without affecting the privacy guarantees. We present a new clustering method with a specially designed distance function that considers the effect of sensitive terms in the privacy goal as part of the clustering process. In this way, when the clustering minimises the total intra-cluster distances of the partition, the utility loss is also minimised. We present two algorithms DocClust and DetK for clustering transactions and determining the best number of clusters respectively.

AB - This work aims to maximise the utility of published data for the partition-based anonymisation of transactional data. We make an observation that, by optimising the clustering i.e. horizontal partitioning, the utility of published data can significantly be improved without affecting the privacy guarantees. We present a new clustering method with a specially designed distance function that considers the effect of sensitive terms in the privacy goal as part of the clustering process. In this way, when the clustering minimises the total intra-cluster distances of the partition, the utility loss is also minimised. We present two algorithms DocClust and DetK for clustering transactions and determining the best number of clusters respectively.

KW - Total distance

KW - Utility loss

KW - Privacy model

KW - Term pair

KW - Small cluster size

U2 - 10.1007/978-3-319-57529-2_38

DO - 10.1007/978-3-319-57529-2_38

M3 - Conference paper

SN - 9783319575285

SP - 481

EP - 494

BT - Advances in Knowledge Discovery and Data Mining

A2 - Kim, Jinho

A2 - Shim, Kyuseok

A2 - Cao, Longbing

A2 - Lee, Jae-Gil

A2 - Lin, Xuemin

A2 - Moon, Yang-Sae

PB - Springer International Publishing AG

CY - Cham

T2 - The 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017)

Y2 - 23 May 2017 through 26 May 2017

ER -

Bewong M, Liu J, Liu L, Li J. Utility aware clustering for publishing transactional data. In Kim J, Shim K, Cao L, Lee JG, Lin X, Moon YS, editors, Advances in Knowledge Discovery and Data Mining: 21st Pacific-Asia Conference, PAKDD 2017 Jeju, South Korea, May 23–26, 2017 Proceedings, Part II. Cham: Springer International Publishing AG. 2017. p. 481-494 doi: 10.1007/978-3-319-57529-2_38

Utility aware clustering for publishing transactional data

Abstract

Conference

Access to Document

Fingerprint

Cite this