Reti bayesiane per lo studio del fenomeno degli incidenti stradali tra i giovani in Toscana

TL;DR

This study applies Bayesian probabilistic networks to analyze adolescent road accidents in Tuscany, uncovering relationships between characteristics and risky driving behaviors to inform future causal research.

Contribution

It introduces a Bayesian network approach to model adolescent driving behaviors and accident risk, providing a foundation for causal analysis and prevention strategies.

Findings

Identified key factors linked to risky driving among adolescents.

Developed a probabilistic model for accident risk assessment.

Provided a basis for future causal network development.

Abstract

This paper aims to analyse adolescents' road accidents in Tuscany. The analysis is based on the Database Edit of Osservatorio di Epidemiologia della Toscana. Complexity and heterogeneity of Edit's data represet an interesting scope to apply Machine Learning methods. In particular, in this paper is proposed an analysis based on a Bayesian probabilistic network, used to discover relationships between adolescents' characteristics and behaviours that are more often associated with an audacious driving style. The probabilistic network developed by this study can be considered a useful starting point for follow up reasearches, aiming to develop a causal network, a tool to limit this phenomenon.