Prediction Insolvency of Insurance Companies Using Random Forest

Z. Rustam, G. Saragih

Research output: Contribution to journalConference articlepeer-review

Abstract

Insurance companies have an important role in economy because they support every insured companies, so it is guaranteed financially, therefore is important to predict the insolvency of insurance companies. Insolvency prediction is like an early warning system for insurance companies. Rustam and Yaurita had predicted insolvency of insurance company by using Spanish non-life insurance firm data from Prof. Dr. Maria Jesus Segovia using support vector machines and fuzzy kernel c-means as classifiers (2018). Furthermore, this research is novel based on the use of random forest as a classifier. The result obtained is reported in percentage of accuracy, both in training and testing of random forest, which was 100% while used 50% training data with entropy and the number of estimators is 100 as hyperparameters. This classification, therefore, shows the best value in contrast with prior methods, even though only 50% of training data set was used.

Original languageEnglish
Article number012036
JournalJournal of Physics: Conference Series
Volume1752
Issue number1
DOIs
Publication statusPublished - 15 Feb 2021
Event3rd International Conference on Statistics, Mathematics, Teaching, and Research 2019, ICSMTR 2019 - Makassar, Indonesia
Duration: 9 Oct 201910 Oct 2019

Keywords

  • Prediction insolvency
  • random forest

Fingerprint Dive into the research topics of 'Prediction Insolvency of Insurance Companies Using Random Forest'. Together they form a unique fingerprint.

Cite this