Performance comparative study of machine learning algorithms for automobile insurance fraud detection
Bouzgarne Itri, Mohamed Youssfi, Mohammed Qbadou, Omar Bouattane · 2019
Nowadays, fraud is a major problem facing the insurance industry that Big Data and Machine Learning are trying to solve. This paper deals with the evaluation of the effectiveness and the verifiability of the best-known machine learning algorithms for fraud prediction. We adopted the supervised method applied to automobile data claims of an anonymous insurance company. We aim to propose an approach that improves the relevance of the results of artificial intelligence. The study has demonstrated that RandomForest works better among all algorithms compared.