“…Thus, 1AT contains only seven different classes to be predicted, which are significantly fewer than 3AT, consisting of 297 different accident types to be predicted [10]. Furthermore, other research on building classifiers based on police accident data often focuses on predicting or modelling injury-related parameters, for example, the accident severity or the number of injured people [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], or investigating risk factors [30], [31], [32], [33], [34], [35], [36]. Additionally, models regarding crash type, typically describing how road users hit each other, 1 seem to be part of the research focus [37], [38], [39], [40], [41].…”