Contextual ranking by passive safety of generational classes of light vehicles

Zaïd Ouni (1) , Christophe Denis (2) , Cyril Chauvel (3) , Antoine Chambaz (1)

1 MODAL'X - Modélisation aléatoire de Paris X
2 LAMA - Laboratoire d'Analyse et de Mathématiques Appliquées
3 Laboratoire d'Accidentologie et de Biomécanique

Each year, the BAAC (Bulletin d'Analyse des Accidents Corporels) data set gathers descriptions of traffic accidents on the French public roads involving one or several light vehicles and injuring at least one of the passengers. Each light vehicle can be associated with its " generational class " (GC), a raw description of the vehicle including its date of design, date of entry into service, and size class. In two given contexts of accident, two light vehicles with two different GCs do not necessarily offer the same level of safety to their passengers. The objective of this study is to assess to which extent more recent generations of light vehicles are safer than older ones based on the BAAC data set. We rely on " scoring " : we look for a score function that associates any context of accident and any GC with a real number in such a way that the smaller is this number, the safer is the GC in the given context. A better score function is learned from the BAAC data set by cross-validation, under the form of an optimal convex combination of score functions produced by a library of ranking algorithms by scoring. An oracle inequality illustrates the performances of the resulting meta-algorithm. We implement it, apply it, and show some results.

Mots clés: car safety; ensemble learning; oracle inequality

Domaines: Statistiques [math.ST]

Zaïd Ouni, Christophe Denis, Cyril Chauvel, Antoine Chambaz. Contextual ranking by passive safety of generational classes of light vehicles. 2016. ⟨hal-01194515v2⟩