The current role of machine learning and explainability in actuarial science

Actuarial science seeks to evaluate, predict and manage the impact of future events. Nowadays, the actuary faces the challenge of predicting and managing risks efficiently, with a universe of information growing exponentially in real-time and with a business dynamic that demands constant competitive...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lozano, Catalina, Romero, Francisco P., Serrano-Guerrero, Jesus, Olivas, Jose A.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2021
Materias:
Ciencias Informáticas
Machine learning
Actuarial Models
Explainability
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125144
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125144
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Machine learning
Actuarial Models
Explainability
spellingShingle Ciencias Informáticas
Machine learning
Actuarial Models
Explainability
Lozano, Catalina
Romero, Francisco P.
Serrano-Guerrero, Jesus
Olivas, Jose A.
The current role of machine learning and explainability in actuarial science
topic_facet Ciencias Informáticas
Machine learning
Actuarial Models
Explainability
description Actuarial science seeks to evaluate, predict and manage the impact of future events. Nowadays, the actuary faces the challenge of predicting and managing risks efficiently, with a universe of information growing exponentially in real-time and with a business dynamic that demands constant competitiveness and innovation. The techniques associated with data engineering and data science open a window of tools that seek, through technology, to improve the processes of product design, pricing, reserves and establishment of market niches practically and realistically, considering the pros and cons that brings the availability and constant updating of information, as well as the computational times that this implies. Therefore, this article aims to review the application of Explainable Machine Learning techniques as an alternative to the development of more efficient and practical actuarial models.
format Objeto de conferencia
Objeto de conferencia
author Lozano, Catalina
Romero, Francisco P.
Serrano-Guerrero, Jesus
Olivas, Jose A.
author_facet Lozano, Catalina
Romero, Francisco P.
Serrano-Guerrero, Jesus
Olivas, Jose A.
author_sort Lozano, Catalina
title The current role of machine learning and explainability in actuarial science
title_short The current role of machine learning and explainability in actuarial science
title_full The current role of machine learning and explainability in actuarial science
title_fullStr The current role of machine learning and explainability in actuarial science
title_full_unstemmed The current role of machine learning and explainability in actuarial science
title_sort current role of machine learning and explainability in actuarial science
publishDate 2021
url http://sedici.unlp.edu.ar/handle/10915/125144
work_keys_str_mv AT lozanocatalina thecurrentroleofmachinelearningandexplainabilityinactuarialscience
AT romerofranciscop thecurrentroleofmachinelearningandexplainabilityinactuarialscience
AT serranoguerrerojesus thecurrentroleofmachinelearningandexplainabilityinactuarialscience
AT olivasjosea thecurrentroleofmachinelearningandexplainabilityinactuarialscience
AT lozanocatalina currentroleofmachinelearningandexplainabilityinactuarialscience
AT romerofranciscop currentroleofmachinelearningandexplainabilityinactuarialscience
AT serranoguerrerojesus currentroleofmachinelearningandexplainabilityinactuarialscience
AT olivasjosea currentroleofmachinelearningandexplainabilityinactuarialscience
bdutipo_str Repositorios
_version_ 1764820451298639872

Ejemplares similares