Using decision trees to extract decision rules from police reports on road accidents

Abstract

The World Health Organization (WHO) considers that traffic accidents are major public health problem worldwide, for this reason safety managers try to identify the main factors affecting the severity as consequence of road accidents. In order to identify these factors, in this paper, Data Mining (DM) techniques such as Decision Trees (DTs), have been used. A dataset of traffic accidents on rural roads in the province of Granada (Spain) have been analyzed. DTs allow certain decision rules to be extracted. These rules could be used in future road safety campaigns and would enable managers to implement certain priority actions.