Automobile Insurance Fraud Detection: An Overview
Ajay Kini, Rohit Chelluru, Kushang Naik, Dattdeep Naik, Shailendra Aswale, Pratiksha Shetgaonkar
Abstract
Frauds are committed in a highly professional way, due to which companies sometimes fail to identify that any fraud has occurred. Unprofessional frauds are also taking place, but they can be identified easily by the companies. Detecting a fraud traditionally is carried out using manual techniques, but by using data mining and algorithms from machine leaning or deep learning the detection process is automated and the frauds can be detected in a more efficient and structured way with more accuracy. The processing speed of information is gradually increased by using various algorithms of machine learning. The highlight of this survey paper is to compare different methods based on their performance. The algorithms help by detecting crucial patterns found in historical data and recognizing them if found in input data. The survey provides proper understanding of different methodologies used for automobile fraud detection. Sometimes machine learning cannot be used to detect multiple frauds involving behavior changes. We propose a vehicle insurance fraud detection mechanism using LSTM RNN networks. LSTM is commonly used in deep learning to design time series information.