Using a back propagation network combined with grey clustering to forecast policyholder decision to purchase investment-inked insurance

Authors:
Ker-Tah Hsu
Affiliations:
Department of International Business, National Taichung University of Education, 140 Min-Shen Road, TaiChung 40306, Taiwan, ROC
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 6
Cited 0

On the approximate realization of continuous mappings by neural networks

Neural Networks
Managerial applications of neural networks: the case of bank failure predictions

Management Science
Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks

Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks
A Matlab toolbox for grey clustering and fuzzy comprehensive evaluation

Advances in Engineering Software
An intelligent market segmentation system using k-means and particle swarm optimization

Expert Systems with Applications: An International Journal
Training feedforward networks with the Marquardt algorithm

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	12.05

Visualization

Abstract

For life insurance companies, identifying potential buyers of investment-linked insurance from among their existing policyholders may be an effective marketing strategy. The purchase decision, i.e. our dependent variable, is a binary variable. In the current study, we apply artificial neural networks to predict policyholder purchase decision of investment-linked insurance and compare the results with that of logistic regression. Because policyholders of investment-linked insurance bear the investment risk, their risk attitude should have a great impact on their purchase decision. We take financial risk attitude and general risk attitude into account simultaneously. Grey clustering statistic offers an alternative for classifying policyholder risk attitudes. We find that grey clustering is better suited to back propagation neural networks; while the average-and-standard-deviation method is better in combination with logistic regression. Further, financial risk attitudes rather than general risk attitudes may be major influences on policyholders' purchase decisions.