Detecting Fraudulent Motor Insurance Claims Using Support Vector Machines with Adaptive Synthetic Sampling Method
Charles Muranda, Ahmed Abdi Yusuf Ali, Thokozani Shongwe · 2020
Classification algorithms suffer from imbalanced training sets. In the area of detecting fraudulent claims in the insurance industry, fraud cases are rare as compared to the genuine ones. Therefore, algorithms of detecting fraud have fewer training samples of positive cases, leading to lower performance metrics compared to when there are equal cases. In this paper, we propose a machine learning method of detecting fraudulent claims. The proposed method uses the adaptive synthetic sampling method (ADASYN) to remove imbalances in the dataset. We then used Support Vector Machines (SVM) to classify the claim cases. The outcome of the algorithm is compared to the imbalanced datasets and other existing methods.