Classifying Risks On Motor Insurance Policies For IFRS 17 Implementation In General Insurance Companies

Abstract

IFRS 17 is a financial accounting standard issued by the International Financial Reporting System that regulates internationally agreed accounting treatment for insurance contracts. In an effort to increase the accuracy of risk assessment for IFRS 17 adaptation, a good way is needed to classify risks from the insured. Therefore, it is necessary to determine the risk group. Because data from an insurance company is large, the CLARA method is suitable for dealing with the problem. CLARA has a more robust nature of outliers and can be used to handle large amounts of data. After grouping, it is important to know what factors cause a person to enter a certain group. For this, classification analysis is needed. Some classification analysis methods are XGBoost, SVM, and AdaBoost. Extreme Gradient Boosting and Adaptive Boosting is a technique in machine learning for binary or multiclass regression and classification problems that results in predictive models in the form of weak predictive models. Support Vector Machine (SVM) is a technique for making predictions, both in the case of regression and binary or multiclass classification. SVM has the basic principle of linear classifier.