Machine Learning and Insurer Insolvency Prediction

35 Pages Posted: 8 Nov 2023

See all articles by Canchun He

Canchun He

affiliation not provided to SSRN

Dejin Huang

Peking University

Ruo Jia

Department of Risk Management and Insurance, School of Economics, Peking University

Xi Wang

Peking University - School of Economics

Abstract

Solvency and its related ruin theory have long been a central topic in actuarial science and insurance economics. We explore the Structural Artificial Neural Network (SANN), a component-wise machine learning algorithm, to predict the insolvency and failure of insurance companies. This new algorithm enables exploring non-redundant predictive information from Big Data. We show that SANN significantly improves the out-of-sample failure prediction, resulting in an average increase of AUC between 1.83% and 9.55%, compared to traditional machine learning and logistic models, based on a sample of 2,424 insurers from 17 European countries. We also show that macroeconomic and yield information is important in predicting insurer failures, in addition to firm characteristics. This research contributes a new machine learning method, SANN, to the insolvency modelling and prediction in the sense that SANN enables grouping predictors into economic categories, and thus allows firm characteristics and macroeconomic priors as separate disciplines to interact within and between categories.

Keywords: insolvency prediction, machine learning, artificial neural network, ruin theory

Suggested Citation

He, Canchun and Huang, Dejin and Jia, Ruo and Wang, Xi, Machine Learning and Insurer Insolvency Prediction. Available at SSRN: https://ssrn.com/abstract=4626405 or http://dx.doi.org/10.2139/ssrn.4626405

Canchun He

affiliation not provided to SSRN ( email )

No Address Available

Dejin Huang

Peking University ( email )

No. 38 Xueyuan Road
Haidian District
Beijing, 100871
China

Ruo Jia

Department of Risk Management and Insurance, School of Economics, Peking University ( email )

Yiheyuan Rd. 5
Haidian
Beijing, 100871
China

Xi Wang (Contact Author)

Peking University - School of Economics ( email )

Beijing
China

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
57
Abstract Views
1,523
Rank
663,520
PlumX Metrics