Young driver fatal motorcycle accident analysis by jointly maximizing accuracy and information

Dan Halbersberg, Boaz Lerner

Research output: Contribution to journalArticlepeer-review

13 Scopus citations


While young drivers (YDs) constitute ∼10% of the driver population, their fatality rate in motorcycle accidents is up to three times higher. Thus, we are interested in predicting fatal motorcycle accidents (FMAs), and in identifying their key factors and possible causes. Accurate prediction of YD FMAs from data by risk minimization using the 0/1 loss function (i.e., the ordinary classification accuracy) cannot be guaranteed because these accidents are only ∼1% of all YD motorcycle accidents, and classifiers tend to focus on the majority class of minor accidents at the expense of the minority class of fatal ones. Also, classifiers are usually uninformative (providing no information about the distribution of misclassifications), insensitive to error severity (making no distinction between misclassification of fatal accidents as severe or minor), and limited in identifying key factors. We propose to use an information measure (IM) that jointly maximizes accuracy and information and is sensitive to the error distribution and severity. Using a database of ∼3600 motorcycle accidents, a Bayesian network classifier optimized by IM predicted FMAs better than classifiers maximizing accuracy or other predictive or information measures, and identified fatal accident key factors and causal relations.

Original languageEnglish
Pages (from-to)350-361
Number of pages12
JournalAccident Analysis and Prevention
StatePublished - 1 Aug 2019


  • Bayesian network
  • Fatal accidents
  • Information measure
  • Key factors
  • Machine learning
  • Motorcycle
  • Prediction
  • Young drivers

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Safety, Risk, Reliability and Quality
  • Public Health, Environmental and Occupational Health


Dive into the research topics of 'Young driver fatal motorcycle accident analysis by jointly maximizing accuracy and information'. Together they form a unique fingerprint.

Cite this