Geographic ratemaking with spatial embeddings
Contenido multimedia no disponible por derechos de autor o por acceso restringido. Contacte con la institución para más información.
| Tag | 1 | 2 | Valor |
|---|---|---|---|
| LDR | 00000cab a2200000 4500 | ||
| 001 | MAP20220002707 | ||
| 003 | MAP | ||
| 005 | 20220127154931.0 | ||
| 008 | 220127e20220103esp|||p |0|||b|spa d | ||
| 040 | $aMAP$bspa$dMAP | ||
| 084 | $a6 | ||
| 245 | 0 | 0 | $aGeographic ratemaking with spatial embeddings$cChristopher Blier-Wong...[et.al] |
| 520 | $aSpatial data are a rich source of information for actuarial applications: knowledge of a risk's location could improve an insurance company's ratemaking, reserving or risk management processes. Relying on historical geolocated loss data is problematic for areas where it is limited or unavailable. In this paper, we construct spatial embeddings within a complex convolutional neural network representation model using external census data and use them as inputs to a simple predictive model. Compared to spatial interpolation models, our approach leads to smaller predictive bias and reduced variance in most situations. This method also enables us to generate rates in territories with no historical experience. | ||
| 650 | 4 | $0MAPA20080591182$aGerencia de riesgos | |
| 650 | 4 | $0MAPA20080573935$aSeguros no vida | |
| 773 | 0 | $wMAP20077000420$g03/01/2022 Volumen 52 Número 1 - enero 2022 , p. 1-31$x0515-0361$tAstin bulletin$dBelgium : ASTIN and AFIR Sections of the International Actuarial Association |