Wavelet-based feature extraction for mortality projection

Persistent link
MARCXML Dublin Core RDF MODS Cita bibliográfica BibTeX SWAP METS

Record image

Articles Articles Wavelet-based feature extraction for mortality projection - Hainaut, Donatien

Collection: Articles

Title: Wavelet-based feature extraction for mortality projection / Donatien Hainaut, Michel Denuit

Notes: Sumario: Wavelet theory is known to be a powerful tool for compressing and processing time series or images. It consists in projecting a signal on an orthonormal basis of functions that are chosen in order to provide a sparse representation of the data. The first part of this article focuses on smoothing mortality curves by wavelets shrinkage. A chi-square test and a penalized likelihood approach are applied to determine the optimal degree of smoothing. The second part of this article is devoted to mortality forecasting. Wavelet coefficients exhibit clear trends for the Belgian population from 1965 to 2015, they are easy to forecast resulting in predicted future mortality rates. The wavelet-based approach is then compared with some popular actuarial models of LeeCarter type estimated fitted to Belgian, UK, and US populations. The wavelet model outperforms all of them.

Other authors: Denuit, Michel Icono con lupa

Other categories: 6

Derechos: In Copyright (InC): http://rightsstatements.org/vocab/InC/1.0/

See issue detail See issue detail