A Comparison of Neural Network, Statistical Methods, and Variable Choice for Life Insurers' Financial Distress Prediction

Abstract

This study examines the effect of the statistical/mathematical model selected and the variable set considered on the ability to identify financially troubled life insurers. Models considered are two artificial neural network methods (back-propagation and learning vector quantization (LVQ)) and two more standard statistical methods (multiple discriminant analysis and logistic regression analysis). The variable sets considered are the insurance regulatory information system (IRIS) variables, the financial analysis solvency tracking (FAST) variables, and Texas early warning information system (EWIS) variables, and a data set consisting of twenty-two variables selected by us in conjunction with the research staff at TDI and a review of the insolvency prediction literature. The results show that the back-propagation (BP) and LVQ outperform the traditional statistical approaches for all four variable sets with a consistent superiority across the two different evaluation criteria (total misclassification cost and resubstitution risk criteria), and that the twenty-two variables and the Texas EWIS variable sets are more efficient than the IRIS and the FAST variable sets for identification of financially troubled life insurers in most comparisons. Copyright The Journal of Risk and Insurance, 2006.

The persistence of hedge fund strategies in different economic periods: A support vector machine approach

“…NN has been successfully used in many areas including finance and economics. [15][16][17] There are few papers in the finance area that explore the use of SVM in finance. 18 The reason is that interest in SVM as a prediction and classification tool is relatively new.…”

A Competing Risks Dynamic Hazard Approach to Investigate the Insolvency Outcomes of Property-Casualty Insurers

“…Net premiums written as a per cent of gross premiums written Net premiums written/Average capital and surplus (%) Ambrose and Seward (1988), Harrington and Nelson (1986), Carson and Hoyt (1995), Lee and Urrutia (1996), Barniv et al (1999), Browne et al (2001), Carson and Hoyt (2003), Brockett et al (2006) Net premium written as a per cent of capital and surplus Net premiums written growth (%) Ambrose and Seward (1988), Kim et al (1995), Lee and Urrutia (1996), Pottier and Sommer (1999), Chen and Wong (2004), Brockett et al (2006), Sharpe and Stadnik (2007) Growth in net premium written…”

Study of Discrete Choice Models and Adaptive Neuro-Fuzzy Inference System in the Prediction of Economic Crisis Periods in USA

“…We propose the scientific findings and methods of artificial intelligence because most studies have found superior results, especially in stock returns and economic data prediction than the common Logit models and Multiple discriminant Analysis among others (Salchenberger et al 1992, coats and Fant 1993, Zhang et al 1999, Fan and Palaniswami 2000, Brockett et al 2006, Ni and Yin 2009, Giovanis 2010. Thus, economists and financial managers should adopt in their portfolio of research tools the artificial intelligence methods and approaches.…”