Risk assessment using artificial neural networks in health insurance sector

Çekyay B., ÖNSEL EKİCİ Ş.

35th International Conference on Computers and Industrial Engineering, ICC and IE 2005, İstanbul, Türkiye, 19 - 22 Haziran 2005, ss.471-474, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.471-474
  • Anahtar Kelimeler: Artificial neural networks, Health insurance, Multiplayer feedforward nets, Self organizing maps
  • Yıldız Teknik Üniversitesi Adresli: Hayır

Özet

Risk assessment is critical in insurance sector. However, especially for health insurance, the risk of a claim is dependent on many variables about the potential customer and there is quite a nonlinear relationship between the specifications of the customer and amount of his/her future claim. For this purpose, this paper proposes the use of artificial neural networks for risk assessment in health insurance sector. In this study, a two stage decision support model is structured using both Kohonen self organizing map and multiplayer feedforward network in order to make risk assessment process more effectively.