Marrying deep learning within blockchain technology for credit card fraud prevention

Abstract

Over the last decade or so, an excessive turnout on e-financial transactions by companies and customers results in a pinnacle growth of credit card fraudulent acts, leading them to lose frequently huge amounts of money. In their trial to find the key to this issue, specialists and experts have founded a bunch of fraud detection and prevention models relied on data mining, machine learning and deep learning. Yet, the outcomes were not effective nor optimal. Thereupon, to foster these prototypes’ function, Blockchain -a safe, decentralized and unchangeable database- was deployed to ban any sort of anomaly or data alteration after storing. For identifying malicious financial behaviours, our work managed to intermingle a pre-designed deep learning prototype with Blockchain. That is to say -for the sake of preventing fraudulence that concerns credit card- we applied the former prototype in Blockchain system. Still, Blockchain showed impotence in terms of using off-chain data, which embeds deep learning pattern, specifically through smart contract. Hence, we activated chainlink boosting our model to surmount this obstacle.