Volume 12, No 1, 2015
Crime vs. demographic factors revisited: Application of data mining methods
Xingan Li, Henry Joutsijoki, Jorma Laurikkala and Martti Juhola
Abstract
The aim of this article is to inquire about correlations between criminal phenomena and demographic factors. This international-level comparative study used a dataset covering 56 countries and 28 attributes. The data were processed with the Self-Organizing Map (SOM), assisted other clustering methods, and several statistical methods for obtaining comparable results. The article is an exploratory application of the SOM in mapping criminal phenomena through processing of multivariate data. We found out that SOM was able to group efficiently the present data and characterize these different groups. Other machine learning methods were applied to ensure groups computed with SOM. The correlations obtained between attributes were chiefly weak.
Pages: 1-17
Keywords: Data mining; Self-organizing map; K-means clustering; Discriminant analysis; K-nearest neighbor classifier; Naïve Bayes classification; Decision trees; Support vector machines (SVMs); Crime; Demographic factors