A study on the occurrence of crimes due to climate changes using decision tree

Abstract

In this study, we figured out what relationship the elements (weather, temperature, precipitation, wind speed, humidity) of meteorological changes have with the incidence of the five violent crimes through data mining. For the data used in this study, the number of meteorological occurrences from January 1, 2011 to March 30, 2012 through portal sites and the elements of meteorological changes of the day recorded in the Korea Meteorological Administration were used as materials. In this study, an analysis was made using the C4.5 algorithm of decision tree to verify what crimes occur according to the elements of the climate change. As a result of such an analysis, most of the crimes were high in the incidence in the following meteorological conditions: when the weather is cloudy; when the temperature is more than 9°C; when the precipitation is less than 10 mm; when the wind speed is less than 4 m/s; and the humidity is more than 50 %. Given these meteorological conditions, cloudy weather showed the highest rate of crime incidence. © 2013 Springer Science+Business Media.