
Research Article
Machine Learning for Insurance Fraud Detection
@INPROCEEDINGS{10.1007/978-3-031-51572-9_5, author={Maria Chousa Santos and Teresa Pereira and Isabel Mendes and Ant\^{o}nio Amaral}, title={Machine Learning for Insurance Fraud Detection}, proceedings={Internet of Everything. Second EAI International Conference, IoECon 2023, Guimar\"{a}es, Portugal, September 28-29, 2023, Proceedings}, proceedings_a={IOECON}, year={2024}, month={2}, keywords={Insurance Fraud Machine Learning-IoE Artificial Intelligence}, doi={10.1007/978-3-031-51572-9_5} }
- Maria Chousa Santos
Teresa Pereira
Isabel Mendes
António Amaral
Year: 2024
Machine Learning for Insurance Fraud Detection
IOECON
Springer
DOI: 10.1007/978-3-031-51572-9_5
Abstract
Fraudulent activities are a complex problem, and still evolve in a continual basis in all company sectors. These activities are considered as one of the major difficulties the insurance companies have to deal with on a daily basis. Thus, insurers are looking for ways to effectively manage, control, and mitigate fraud. In addition, improving profits by minimizing fraud is the main goal. The exponential amount of information collected, and the technology evolvement has been a strategy to address frauds. The Internet of Everything enables organizations to access diverse information’s resources through the interconnection of people-to-machines, which involves machines, data and people, contributing to increase their knowledge and intelligence. In the world of technology, Machine Learning has been widely implemented in multiple contexts. The insurers companies start using Machine Learning to support the detection of fraudulent complaints through the application of algorithms aimed to find patterns in a database, which are hidden through a large amount of data. This paper intends to present the use of Machine Learning technology to support the insurers companies to detect fraudulent activities and further analyze the impacts of technology in people and thus enable to achieve a more rapid and accurate information.