Title :
A neural network model for the evaluation of Dutch non-life insurance companies
Author_Institution :
Fac. of Manage. & Organ., Groningen Univ., Netherlands
Abstract :
Based on six financial ratios, a one-hidden-layer back-propagation neural network classifies Dutch non-life insurance companies as strong moderate, or weak. The network shows very good performance for weak and strong companies (95% correct), but completely fails to recognize moderate companies. The relative importance of each input variable is analyzed by calculating the strength of the relationship between each input and each output variable
Keywords :
backpropagation; insurance data processing; neural nets; Dutch nonlife insurance companies; financial ratios; input variable; one-hidden-layer back-propagation neural network; Government; Industrial relations; Input variables; Insurance; Job shop scheduling; Logistics; Neural networks; Neurons; Processor scheduling; Protection;
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1995. Proceedings., Second New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-7174-2
DOI :
10.1109/ANNES.1995.499499
