USING ADVANCED ANALYTICS IN FRAUD DETECTION AND FINANCIAL CRIME PREVENTION IN FINANCIAL INSTITUTIONS ACROSS THE UNITED STATES
Main Article Content
Abstract
: Banks and financial institutions in the U.S. are facing more and more challenges in fighting fraud and financial crime. Crimes like identity theft, money laundering, account takeovers, and payment scams are growing, especially as more people use mobile banking, peer-to-peer apps, and instant payments. Traditional fraud systems based on fixed rules can’t keep up with modern scams, which now include fake identities, bot attacks, and complicated laundering schemes (Consumer Financial Protection Bureau [CFPB], 2023; KPMG, 2025). This study looks at how advanced analytics, including machine learning (ML), anomaly detection, and natural language processing (NLP) can help stop fraud more effectively. We used transaction data from five U.S. banks (from 2022 to 2024) and trained smart models using customer behavior, time patterns, and location data.
The results were impressive: Fraud detection accuracy went up from 74% to 93%, and False alarms dropped by 48%
New types of fraud (missed by older systems) were caught 70% of the time using unsupervised models like clustering and autoencoders. There was also a strong match between the model’s risk scores and real fraud cases (correlation of r = 0.88, p < .001) (Federal Reserve, 2024). NLP tools were also successful, reaching an F1-score of 0.89, in identifying issues in transaction notes and documents like fake companies, unclear ownership, or risky countries (FinCEN, 2023). These findings show that using analytics makes fraud detection faster, smarter, and more flexible. It helps banks catch fraud in real time, follow government rules (like the Bank Secrecy Act and AML regulations), and improve fraud investigation and reporting. This paper recommends that banks use these analytics tools throughout the entire fraud prevention process, from live monitoring to post-fraud reviews and compliance reporting.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.