A time-efficient model for detecting fraudulent health insurance claims using Artificial neural networks

Health insurance has come in rescue for people, in reducing their medical expenditure, which otherwise would have taken a high toll on their income. There are both private and government-funded agencies serving in the health insurance sector. With soaring high demand among the public, healthcare is not safe from the fraudsters. The usage of computerized techniques has proved this area even more vulnerable. It has become highly essential to detect this fraud at the earliest, such that the impact of loss could be minimized. This paper throws light on a framework in detecting fraud with faster learning and identifying the maximum number of fraud instances. The usual problems, like data heterogeneity and imbalanced classification of classes, have also been discussed in this paper. As a part of developing an efficient framework for fraud detection, we applied several learners and optimization techniques. The framework has evaluated with claims dataset obtained from the CMS Medicare facility. We finally reached to a conclusion that the application of Multi-Layer Perceptron, a feed-forward Neural Network with genetic algorithm optimization had helped in enhancing the results and gain higher accuracy. PCA was also applied to pick the most significant variables. The use of PCA and other appropriate pre-processing techniques has also helped us in reducing the training time, thereby achieving efficiency in terms of accuracy and speed.