Vehicle Insurance Claim frequency and Amount Prediction through Machine Learning and Vehicle Analytics

Gangaramrao, Arun (2023) Vehicle Insurance Claim frequency and Amount Prediction through Machine Learning and Vehicle Analytics. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study explores the application of machine learning models for forecasting auto insurance claim severity and amounts across diverse datasets, optimizing risk assessment and claim processing. Leveraging three datasets, classification algorithms such as Logistic Regression, Random Forest, and Adaboost, and regression algorithms including Gradient Boost, Random Forest, SVR, Decision Tree, and Bayesian Regression are employed. While Adaboost faces challenges, Logistic Regression and Random Forest excel in multiclass classification and handle imbalanced classes well. In binary classification tasks, Random Forest consistently demonstrates superior performance across all datasets, achieving an impressive average accuracy of 98. On the other hand, when predicting claim amounts in regression tasks, Decision Tree emerges as the standout performer, particularly excelling in dataset 2 with a remarkable Mean Absolute Error (MAE) score of 77.49. Notably, Random Forest Regressor exhibits exceptional results in dataset 1, surpassing other models in accuracy and prediction effectiveness. The findings underscore the importance of considering dataset-specific features and class imbalances in model selection, providing valuable insights for improving predictive capabilities. Future work is proposed to further enhance these applications through customized model extensions and a deeper understanding of class imbalances and dataset features.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Moldovan, Arghir Nicolae UNSPECIFIED
Uncontrolled Keywords:	Claim Frequency; Usage Based Insurance; Machine Learning; Claim Amount; Classification; Regression
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics H Social Sciences > HG Finance > Insurance Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Motor Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	08 May 2025 11:07
Last Modified:	08 May 2025 11:07
URI:	https://norma.ncirl.ie/id/eprint/7513

Actions (login required)

View Item