NORMA eResearch @NCI Library

A Comparative Study of Ensemble Techniques and Individual Classifiers in Predicting Insurance Claim

Njoh-Paul, Ifeoma Marian (2020) A Comparative Study of Ensemble Techniques and Individual Classifiers in Predicting Insurance Claim. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

The insurance industry has grown rapidly and is significantly playing an important role in the economy of a country. However, one lingering issue faced by insurers is being able to correctly predict if a policyholder will lay a claim so as to determine a fair price to be charged for purchasing an insurance policy. The goal of this research is to make a comparison between individual classifiers and ensemble techniques to determine which provides the best predictive results. The Knowledge Discovery in Database (KDD) process was adopted to gain insight and business knowledge from the dataset. Four individual classifiers, Support Vector Machine, Linear Discriminate Analysis, Logistic regression and Artificial Neural Network along with two ensemble techniques, Extreme Gradient boosting and stacking were used, the research discovered that the ensemble techniques used gave a better predictive result than all the selected individual classifiers. XGBoost had an accuracy of 96% while stacking algorithm had 76%. The performance metrics chosen for this research was accuracy, sensitivity and AUC.
Keywords: Insurance claim, Ensemble, Prediction, Stacking, Support Vector Machine, Linear Discriminate Analysis, Extreme Gradient Boosting, Logistic regression, Artificial Neural Network.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

H Social Sciences > HG Finance > Insurance
Divisions: School of Computing > Master of Science in FinTech
Depositing User: Dan English
Date Deposited: 29 Jan 2021 17:09
Last Modified: 29 Jan 2021 17:09
URI: http://norma.ncirl.ie/id/eprint/4573

Actions (login required)

View Item View Item