An Approach for Variable Selection and Prediction Model for Estimating the Risk-Based Capital (RBC) Based on Machine Learning Algorithms

Jaewon Park,Minsoo Shin

doi:10.3390/risks10010013

Abstract

The risk-based capital (RBC) ratio, an insurance company’s financial soundness system, evaluates the capital adequacy needed to withstand unexpected losses. Therefore, continuous institutional improvement has been made to monitor the financial solvency of companies and protect consumers’ rights, and improvement of solvency systems has been researched. The primary purpose of this study is to find a set of important predictors to estimate the RBC ratio of life insurance companies in a large number of variables (1891), which includes crucial finance and management indices collected from all Korean insurers quarterly under regulation for transparent management information. This study employs a combination of Machine learning techniques: Random Forest algorithms and the Bayesian Regulatory Neural Network (BRNN). The combination of Random Forest algorithms and BRNN predicts the next period’s RBC ratio better than the conventional statistical method, which uses ordinary least-squares regression (OLS). As a result of the findings from Machine learning techniques, a set of important predictors is found within three categories: liabilities and expenses, other financial predictors, and predictors from business performance. The dataset of 23 companies with 1891 variables was used in this study from March 2008 to December 2018 with quarterly updates for each year.

Highlights

IntroductionLife insurance is one of the most important financial products for sustainable finance and sustainability in financial consumers
Unlike many studies that have focused on comparing the predictive power of several Machine learning approaches, the purpose of our study is to find a set of important predictors to estimate the risk-based capital (RBC) ratio of all Korean life insurance companies that have not yet been studied
In the quarter, including RBC ratiot-1, total shareholders’ equity (%), total liabilities (%), policy reserve (%), insurance contract liabilities (%), small- and medium-sized enterprise (SME) loans (%), general accounts with available-for-sale (AFS) security investments (%), non-financial assets (%), claims paid to the group, premium reserves for insurance (%), large corporate loans (%), household loans secured by real estate (%), SME loans (Won), allowances for loan losses by loan type of SME loans, general account refunds for claims paid to the group, annual premiums as a type of premium, financial liabilities by amortized cost, and so on

Summary

Introduction

Life insurance is one of the most important financial products for sustainable finance and sustainability in financial consumers. Life insurance companies deal with financial products (i.e., life insurance policies) that are critically related to a household’s financial security after a cataclysmic event (i.e., loss of a breadwinner) (Rejda 2008; Thoyts 2010). Any failure in supervising the life insurance companies can be critically associated with households’ financial well-being (Financial Supervisory Service 2017). As a financial product for survivors, life insurance serves the primary function of securing a certain amount of wealth, which can help recover a financial loss incurred by the premature death of a breadwinner (Rejda 2008; Thoyts 2010). Insurance policyholders, financial educators, policymakers, and insurers need to understand which factors are associated with life insurance companies’ stability and reliability to build a sustainable financial environment

Objectives

Methods

Results

Conclusion