Frequent itemsets mining based on different levels of privacy

The challenge of mining all frequent item sets in a transactional dataset whose supports are above a particular threshold through the restriction that the results of the mining can not compromise the confidentiality of any one transaction is known as frequent item sets mining with different levels o...

Full description

Saved in:
Bibliographic Details
Main Authors: Suresh, A., Anandam, D., Reddy, P. V. Subba
Format: Conference Proceeding
Language:English
Subjects:
Data mining
Datasets
Privacy
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The challenge of mining all frequent item sets in a transactional dataset whose supports are above a particular threshold through the restriction that the results of the mining can not compromise the confidentiality of any one transaction is known as frequent item sets mining with different levels of secrecy. Over a large amount of data, proposed methods for this challenge are unable to strike a good balance between efficiency, privacy, and data value. In this paper, proposed an efficient, different level of private frequent item sets mining technique for high dimensionality data to achieve this goal. Our technique decreases compute effort, based on ideas of sampling and transaction reduction using a length restriction, reduces mining vulnerability and hence improves data usefulness given a set privacy budget. On various datasets, experimental findings validates that our technique performs well compared to previous techniques.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0117557