Spatial modelling of driver crash risk using georeferenced data

Riccardo Borgoni, Andrea Gilardi, Diego Zappa*

*Autore corrispondente per questo lavoro

Risultato della ricerca: Contributo in libroChapter


This contribution deals with a quite common but relevant issue in insurance. Suppose to be interested in covering a risk (e.g. motor accident, life/health risks, risk of disability, adverse weather events, etc…) and that you want to stipulate a contract to protect yourself against the loss of economic resources in case that the event occurs. In such circumstances any insurer will ask you to pay an amount (called premium) that approximately equals the pure premium (i.e. the amount that corresponds to the expected loss times the odds of the event) plus the so called loadings (i.e. the amount of money that consider both the gain of the contractor and administrative/process costs). The challenging point is: how to compute the odds? In particular, how to compute the probability of an adverse event given covariates that should be considered explanatory of the risk? [...]
Lingua originaleEnglish
Titolo della pubblicazione ospiteNew Economic & Statistical Perspectives on Urban and Territorial Themes (NESPUTT 2019). Book of Short Papers and Proceedings
EditorMichelangeli Alessandra Borgoni Riccardo
Numero di pagine4
Stato di pubblicazionePubblicato - 2020


  • Geospatial modelling
  • Insurance Premiums
  • Risk of accidents


Entra nei temi di ricerca di 'Spatial modelling of driver crash risk using georeferenced data'. Insieme formano una fingerprint unica.

Cita questo