Owing to the volatile nature of the market, the slowdown in economic growth, and the rapid upsurge of digital e-commerce, the issue of fraud has become increasingly prevalent. The continuous evolution of electronic commerce technology has led to a significant increase in credit card usage, establishing it as the favored method of payment for both online and offline transactions. Consequently, the rise in credit card fraud has become apparent, affecting individuals seeking smart cards and loans, who now have the choice of applying for credit cards through online channels or traditional paper forms. Unfortunately, these application processes have exposed instances of fraudulent activities, notably identity theft, which poses a significant concern for both credit cardholders and financial institutions. Dishonest actors are unlawfully obtaining customer’s identities and gaining unauthorized access to credit cards, thereby posing substantial risks for both customers and financial entities.However, the existing strategies that rely on business rules and scorecards for fraud detection, without utilizing data mining, have shown limitations. In response to these shortcomings, this study introduces an innovative method for real-time fraud detection during the application phase. This method involves implementing a novel multi-layer fraud tracking system based on data mining algorithms. This system comprises two distinct algorithms, namely communal tracing and spike tracing, working together to improve the accuracy, speed, and efficiency of fraud detection procedures. By validating applications in real-time upon submission, this system acts as a robust deterrent against the approval of fraudulent credit card applications before issuance.