Raju, Dhanush (2024) Identifying the probability of the Natural Disaster to help the Insurance Company to take decisions on providing Insurance. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (797kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (640kB) | Preview |
Abstract
The aim of this study is to determine the probability of natural disasters occurring in a specific area, with the purpose of aiding Insurance companies in making well-informed choices, The process involves in the analysis of an extensive historical data, meteorological data, and statistical models based on either the parent insurance company or the third party insurance providers. Historical data on past catastrophes or natural disaster is collected and analyzed with meteorological factors associated with the occurrence of disasters. Statistical models, such as logistic regression and other machine learning algorithms like xgboost, light gradient boosting (LGBM), random forest are used to predict the likelihood of future disasters. We propose a response system which helps in the decision making of the insurance companies to save the claim amounts for a risk management of the company. The findings offer different useful insights that can inform decision-making in insurance companies, allowing them to make required adjustments to pricing, coverage restrictions, and risk mitigation strategies. Here we make a propensity based triple stage system which uses LGBM model due to its high performance and light weight to predict the propensity of the natural disasters. While for detecting the suspicious fraud model, similar model with different hypermeter tuning is used. The third stage is response system which can be used to deploy and find those cases which are prune to high risk areas and no suspicious.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Heeney, Sean UNSPECIFIED Cosgrave, Noel UNSPECIFIED |
Uncontrolled Keywords: | Insurance; Risk Analysis; Machine Learning; Finance; Impact Assessment; Multimodal Risk Management; Impact Analysis |
Subjects: | H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management H Social Sciences > HG Finance H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech H Social Sciences > HG Finance > Insurance Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in FinTech |
Depositing User: | Ciara O'Brien |
Date Deposited: | 05 Aug 2025 11:54 |
Last Modified: | 05 Aug 2025 11:54 |
URI: | https://norma.ncirl.ie/id/eprint/8434 |
Actions (login required)
![]() |
View Item |