Development of crime in England and Wales 1898–2001: Data mining using self-organising map

The aim of this article is to inquire about historical development of criminal phenomena in England and Wales, and relationship between different crime rates, based on a set of English and Welsh historical data. This national-level study uses a dataset covering 103 years (1898–2001, with data of 1939 missing and not counted) and 50 attributes. The collected data are clustered with Self-Organizing Map (SOM) and the features are assessed using Scatter algorithm. Several machine learning methods are applied to verify the clustering result obtained by the SOM. Accuracy of 96.2% gained by one-vs-one least-squares support vector machines shows that the clusters obtained by the SOM are valid. The article is an exploratory application of the SOM in research of criminal phenomena through processing of multivariate data. The research showed that SOM was able to cluster efficiently the present data and to characterize these different clusters.