Data Mining and Official Statistics: The Past, the Present and the Future

Big Data. 2014 Mar;2(1):34-43. doi: 10.1089/big.2013.0038. Epub 2014 Feb 19.

Abstract

Along with the increasing availability of large databases under the purview of National Statistical Institutes, the application of data mining techniques to official statistics is now a hot topic that is far more important at present than it was ever before. Presented in this article is a thorough review of published work to date on the application of data mining in official statistics, and on identification of the techniques that have been explored. In addition, the importance of data mining to official statistics is flagged and a summary of the challenges that have hindered its development over the course of the last two decades is presented.