Maximising accuracy and efficiency of traffic accident prediction combining information mining with computational intelligence approaches and decision trees

The development of universal methodologies for the accurate, efficient, and timely prediction of traffic accident location and severity constitutes a crucial endeavour. In this piece of research, the best combinations of salient accident-related parameters and accurate accident severity prediction models are determined for the 2005 accident dataset brought together by the Republic of Cyprus Police. The optimal methodology involves: (a) information mining in the form of feature selection of the accident parameters that maximise prediction accuracy (implemented via scatter search), followed by feature extraction (implemented via principal component analysis) and selection of the minimal number of components that contain the salient information of the original parameters, which combined bring about an overall 74.42% reduction in the dataset dimensionality; (b) accident severity prediction via probabilistic neural networks and random forests, both of which independently accomplish over 96% correct prediction and a balanced proportion of under- and over-estimations of accident severity. An explanation of the superiority of the optimal combinations of parameters and models is given, as is a comparison with existing accident classification/prediction approaches.