Title: | Deep learning in life insurance risk prediction | Language: | English | Authors: | Gerharter, Caroline | Qualification level: | Diploma | Keywords: | Lebensversicherungsrisiko; Künstliches neuronales Netz Life insurance risk; artificial neural network |
Advisor: | Rheinländer, Thorsten | Issue Date: | 2019 | Number of Pages: | 40 | Qualification level: | Diploma | Abstract: | This diploma thesis deals with the implementation of an artificial neural network to predict life insurance risks. At first, general terms of deep learning are declared and defined. A brief insight into life insurance risk, specifically into the crucial parameter, the probability of dying, is given. Consequently, the structure of a deep neural network, the different activation functions and optimisers are explained in detail. This also includes a precise explanation of the training algorithm of a deep neural network. Finally, the calculation of the probability of dying is performed. Several experiments are carried out to test different scenarios for the neural network and the simulations are thoroughly analysed. In conclusion, the calculation of the probability of dying via an artificial neural network worked exceptionally well. A model with four hidden layers, overall 640 neurons, the Adam optimiser and either the ELU, TanH or Softplus activation function yielded by far the best results for this problem. |
URI: | https://resolver.obvsg.at/urn:nbn:at:at-ubtuw:1-132365 http://hdl.handle.net/20.500.12708/11451 |
Library ID: | AC15536163 | Organisation: | E105 - Institut für Stochastik und Wirtschaftsmathematik | Publication Type: | Thesis Hochschulschrift |
Appears in Collections: | Thesis |
Files in this item:
File | Description | Size | Format | |
---|---|---|---|---|
Deep learning in life insurance risk prediction.pdf | 2.82 MB | Adobe PDF | ![]() View/Open |
Page view(s)
18
checked on Feb 18, 2021
Download(s)
33
checked on Feb 18, 2021

Google ScholarTM
Check
Items in reposiTUm are protected by copyright, with all rights reserved, unless otherwise indicated.