Title:	BIG DATA ANALYTICS IN THE PUBLIC SECTOR: A CASE STUDY OF NEET ANALYSIS FOR THE LONDON BOROUGHS
Author(s):	Daqing Chen, Babatunde Asaolu, Chao Qin
ISBN:	978-989-8533-54-8
Editors:	Piet Kommers and Guo Chao Peng
Year:	2016
Edition:	Single
Keywords:	Big data analytics, NEET analysis, k-means clustering, Hierarchical clustering, SAS Enterprise Miner, Tableau
Type:	Full Paper
First Page:	171
Last Page:	178
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	For decades, the issue of young people who are aged 16 -18 and not in employment, education, or training (NEET) has been a major concern for governments and local authorities. In this paper, a big data perspective is taken to examine the NEET issue in order to highlight factors that are correlated with NEET, the negative consequences and causes of NEET, and potential solutions to NEET. The NEET dataset about the 33 London Boroughs has been considered along with other seven datasets relating to population, crime offences, benefits claimants, median property price, active businesses, immigrants, and conception under 18. All the datasets are public-accessible and comprise a data collection of the same period of time from 2009 to 2013. Each of them represents a particular measure. Hierarchical variable clustering, k-means clustering, and correlation analysis have been conducted using SAS Enterprise Miner and Tableau in this work. These tools enable us to analyse the problem in a multi-dimensional, hierarchical, integrated, and longitudinal way. The research has demonstrated that a) The NEET issue is much more severe in outer London than in inner London; b) The main factors correlated with NEET vary from inner London to outer London; c) Each of the measures considered has a certain correlation strength with the NEET rate, and amongst them, median property price is a simple and seemingly accurate indicator of areas likely to suffer from NEET and thus to take appropriate precautions in order to reduce the likelihood of further increases in NEET; and d) The London Boroughs can be grouped based on similarities in terms of a set of given measures, and the memberships of the groups remain stable.
	Go Back