AbstractCredit card fraud is growing along with the development of technology in today’s world. Hundreds of researches have been made in the past for more than four decades and still, the problem is critical, affecting large financial and banking companies. In this paper, we are focusing on the design and development of an advanced real-time credit card fraud detection framework with the help of big data technologies from one of the leading public cloud providers, Microsoft Azure. We have designed the complete framework to satisfy most current fraud detection systems which could process a large amount of data in real-time and improve the accuracy by implementing multiple machine learning algorithms. We further implemented multiple layers of the workflow including the ingestion layer, streaming layer, processing and transformation layer, model training and scoring layer and storage layer. With the help of these, we were able to build massive storage, fast detection, model training, and real-time fraud detection system. This paper aims in designing the modern credit card fraud detection system and has been tested by a sample dataset to achieve our goal.
SubjectsCredit card fraud, Microsoft Azure, SGD classifier, Extreme random trees
RightsCopyright for scholarly resources published in RUcore is retained by the copyright holder. By virtue of its appearance in this open access medium, you are free to use this resource, with proper attribution, in educational and other non-commercial settings. Other uses, such as reproduction or republication, may require the permission of the copyright holder.