Limitações do uso dos modelos de árvore de classificação na investigação da severidade de acidentes rodoviários

The objective of this study is to discuss the main limitations encountered in the classification process of traffic accident severity, based on decision tree models (CART). With this purpose, CART was used in the mining of an unbalanced database of road accidents, considering injury severity, categorized as accidents without victims and with victims (fatal and non-fatal), as the dependent variable. The variables associated with accident characteristics, road infrastructure and environmental conditions were used to identify the influence of these factors on accident severity. Although the classification by CART resulted in a high accuracy overall, it resulted in a low rate of accuracy in the classification of accidents with victims, which correspond to the rarest observations in the database. In addition, it resulted in a high number of decision rules, considering the number of categories of independent variables in the prediction process of the target variable. The results indicated that CART is not efficient in the study of multiple-effect phenomena, such as road accidents, since it does not have the potential to associate a large number of parameters, which restricts the analysis and interpretation of the results to the binary structure of the tree. Thus, an exploratory analysis of the database is suggested, when it is desired to analyze the influence of a specific category of a database variable in the occurrence of traffic accidents.