By exploiting Natural Language Processing techniques we aim at grasping latent information useful for insurance to tune policy premiums. By using a large set of police reports, we classify medical and police reports based upon the profile of the people involved and according to the relevance of their content. At a second step, we match these risks with the customer profiles of a company in order to add new and relevant risk covariates to improve the precision and the determination of policy premiums.
Borrelli, M., Zappa, D., From unstructured data and word vectorization to meaning: text mining in insurance, in Greselin, F. M. F. Z. M. (ed.), Cladag 2017, Book of Short Papers, Universitas Studiorum S.r.l., Milano 2017: 243- 248 [https://hdl.handle.net/10807/105442]
From unstructured data and word vectorization to meaning: text mining in insurance
Zappa, DiegoUltimo
2017
Abstract
By exploiting Natural Language Processing techniques we aim at grasping latent information useful for insurance to tune policy premiums. By using a large set of police reports, we classify medical and police reports based upon the profile of the people involved and according to the relevance of their content. At a second step, we match these risks with the customer profiles of a company in order to add new and relevant risk covariates to improve the precision and the determination of policy premiums.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
