Authors: Sudhanshu Gupta, Avinash Aganihotri, Harsh Sharma, Tanya Handa
Abstract: More people understand the use of technology and that is being used on their daily life. This will increase the chances of losing valuable data and information to the scammers who might use your data for your own detriment or have a word or a spell with you or harm you in any possible manner or way. Consequently, fraud detection Systems are employed in different fields of businesses such as banking, e-commerce, healthcare, and cybers security to identify and terminate fraud. They are essential because of the prevention of monetary losses, the protection of private information, the attainment of client confidence, and compliant with legal requirements. Some of the modern systems employ machine learning methods, while supervised learning methods are adopted to ascertain pre-defined fraud patterns and the unsupervised ones to extract anomalies. Techniques to increase precision of the identification of fraud include anomaly detection, graph based method and ensemble. Consequently, to guarantee an effective fraud detection for user it is necessary to find best fraud detection algorithm while maintaining regulatory standards and customer satisfaction , the best fraud detection algorithm must handle all aspects; efficiency, false positive disrupts, F1 score, dealing with imbalanced data and cost.
