Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers

Ernest Goss; Harish Ramchandani

doi:10.1007/BF02920611

Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers

Ernest Goss, Harish Ramchandani

Department of Economics and Finance

Research output: Contribution to journal › Article

16 Citations (Scopus)

Abstract

Past studies have documented the failure of the Insurance Regulatory Information System (IRIS) to provide adequate warning of insurer financial distress or insolvency. As a result, scholars have examined alternative parametric and non-parametric models to predict insurer insolvency. This study uses a neural network, a non-parametric alternative to past techniques, and shows how this methodology predicts insurer insolvency more effectively than parametric models.

Original language	English
Pages (from-to)	1-18
Number of pages	18
Journal	Journal of Economics and Finance
Volume	19
Issue number	3
DOIs	https://doi.org/10.1007/BF02920611
State	Published - Sep 1995

Fingerprint

Insurer

Prediction

Insolvency

Logit regression

Discriminant analysis

Neural networks

Regression analysis

Methodology

Financial distress

Nonparametric model

Insurance

Warning

Information systems

Parametric model

All Science Journal Classification (ASJC) codes

Economics, Econometrics and Finance(all)
Finance
Economics and Econometrics

Cite this

Goss, E., & Ramchandani, H. (1995). Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers. Journal of Economics and Finance, 19(3), 1-18. https://doi.org/10.1007/BF02920611

Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers. / Goss, Ernest; Ramchandani, Harish.

In: Journal of Economics and Finance, Vol. 19, No. 3, 09.1995, p. 1-18.

Research output: Contribution to journal › Article

Goss, E & Ramchandani, H 1995, 'Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers', Journal of Economics and Finance, vol. 19, no. 3, pp. 1-18. https://doi.org/10.1007/BF02920611

Goss E, Ramchandani H. Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers. Journal of Economics and Finance. 1995 Sep;19(3):1-18. https://doi.org/10.1007/BF02920611

Goss, Ernest ; Ramchandani, Harish. / Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers. In: Journal of Economics and Finance. 1995 ; Vol. 19, No. 3. pp. 1-18.

@article{0a6cfe71f3de405a8c4b96f2f17915b6,

title = "Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers",

abstract = "Past studies have documented the failure of the Insurance Regulatory Information System (IRIS) to provide adequate warning of insurer financial distress or insolvency. As a result, scholars have examined alternative parametric and non-parametric models to predict insurer insolvency. This study uses a neural network, a non-parametric alternative to past techniques, and shows how this methodology predicts insurer insolvency more effectively than parametric models.",

author = "Ernest Goss and Harish Ramchandani",

year = "1995",

month = "9",

doi = "10.1007/BF02920611",

language = "English",

volume = "19",

pages = "1--18",

journal = "Journal of Economics and Finance",

issn = "1055-0925",

publisher = "Springer New York",

number = "3",

}

TY - JOUR

T1 - Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers

AU - Goss, Ernest

AU - Ramchandani, Harish

PY - 1995/9

Y1 - 1995/9

N2 - Past studies have documented the failure of the Insurance Regulatory Information System (IRIS) to provide adequate warning of insurer financial distress or insolvency. As a result, scholars have examined alternative parametric and non-parametric models to predict insurer insolvency. This study uses a neural network, a non-parametric alternative to past techniques, and shows how this methodology predicts insurer insolvency more effectively than parametric models.

AB - Past studies have documented the failure of the Insurance Regulatory Information System (IRIS) to provide adequate warning of insurer financial distress or insolvency. As a result, scholars have examined alternative parametric and non-parametric models to predict insurer insolvency. This study uses a neural network, a non-parametric alternative to past techniques, and shows how this methodology predicts insurer insolvency more effectively than parametric models.

UR - http://www.scopus.com/inward/record.url?scp=0141462324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141462324&partnerID=8YFLogxK

U2 - 10.1007/BF02920611

DO - 10.1007/BF02920611

M3 - Article

VL - 19

SP - 1

EP - 18

JO - Journal of Economics and Finance

JF - Journal of Economics and Finance

SN - 1055-0925

IS - 3

ER -

Access to Document

10.1007/BF02920611