Analysis of Fraud Prediction and Detection Through Machine Learning
Kamal Upreti, Alankar Sharma, Vishal Khatri, Sheela Hundekari, Vijay Gautam, Anmol Kapoor
Abstract
In today's world the rate of fraudulent activities has significantly elevated, because of which a need for a competent system is required. Among all the fraudulent activities insurance fraud has the most dominating rate of growth. Fraud studies have suggested, that upon identifying the similar characteristics of a fraudulent claim with the claimants, a system of forensic and data-mining technologies for fraud detection can be set up. In this, seek to define fraud and fraudster, and look at the types of fraud and followed by the consequences of fraud to financial systems. As fraud is getting widespread these days epically in the health care insurance system, dealing with this problem has become a necessity. Unsupervised machine learning algorithms such as K-Means clustering along with supervised algorithms used in machine learning, like support vector machines, logistic regression, design trees etc. can play a very vital role in binary class classifications, which would ultimately help in identifying and outreaching the desired goal of fraudulent detection. In the end, this paper specifies the best or the most appropriate model that could be used in the given dataset to produce the most accurate results, based on certain parameters of confusion metrics like accuracy, precision, and specificity.