Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using Artificial Neural Networks to Predict One Year Population Mortality Rates
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Being able to predict mortality rates is the key factor in any pension or life insurance companies’ business model. Artificial Neural Networks are already being tested and implemented to predict mortality in the field of medical science, with recent studies showing promising results of their predictive power in one year mortality rates. Today, insurance companies in Sweden utilizes the Makeham curve to model and approximate mortality, traditionally with only age and sex being its input features. This study utilized artificial neural networks to model one year mortality rates that could otherwise be derived from the Makeham curve. Features other than sex and age were also included as a part of this study to introduce more features that could affect mortality rate. The network was successful at modelling the one year mortality rates and it was able to distinguish between age, sex and the newly introduced features. It yielded results that were on par with predictions made by the Swedish branch organization of the private insurance companies.

Abstract [sv]

Att kunna förutspå dödlighet är en nyckelfaktor för pensionoch livförsäkringsföretagens affärsmodeller. Man har redan börjat tillämpa och testa artificiella neurala nätverk för att förutspå dödlighet inom medicinska studier. På senare tid har dessa påvisat lovande resultat gällande förutsägningsförmåga för ettårsdödlighet. Idag använder de svenska försäkringsföretagen Makehamkurvan för att modellera dödlighet, traditionellt sett med endast ålder och kön som indata. Artificiella neurala nätverk används i den här studien för att modellera ettårsdödlighet som annars kan härledas från Makehamkurvan. Utöver kön och ålder har även andra särdrag använts. Det visade sig att det neurala nätverket lyckades modellera ettårsdödlighet och kunde särskilja mellan ålder, kön och de nya särdragen. Resultatet var också i nivå med prediktionerna gjorda av Svensk Försäkring.

Place, publisher, year, edition, pages
2019. , p. 45
Series
TRITA-EECS-EX ; 2019:230
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-254974OAI: oai:DiVA.org:kth-254974DiVA, id: diva2:1337074
Educational program
Master of Science - Industrial Engineering and Management
Supervisors
Examiners
Available from: 2019-07-11 Created: 2019-07-11 Last updated: 2019-07-11Bibliographically approved

Open Access in DiVA

fulltext(784 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 784 kBChecksum SHA-512
35f96e4e4eb841d6216f10a157eca6074137a384e6bdb5cbbda4eb373034d94d45fb7c1a5c13f67347a728e95858837c8803b1948cf28b777be067bf8bfd1f0d
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 56 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf