A preprocessing optimization applied to the cell suppression problem in statistical disclosure control

Abstract

As organizations start to publish the data that they collect, either internally or externally, in the form of statistical tables they need to consider the protection of the confidential information held in those tables. The algorithms used to protect the confidential information in these statistical tables are computationally expensive. However a simple preprocessing optimization applied prior to protection can save time, improve the resultant protection and on occasions enable the use of exact methods where otherwise heuristic methods would have been necessary. The theory behind this preprocessing optimization, how it can be applied and its effectiveness are described in this paper.