Checks remain the subject of more fraud than any other payment method, according to the 2018 Association for Financial Professionals (AFP) Payments Fraud and Control Survey. Financial institutions encounter check fraud in many ways: counterfeits, forgeries, alterations, serial number, stop payment, and check kiting.
In order to combat check fraud, successful FIs utilize an automated check fraud solution with extensive mathematical and machine learning methods analyzing both images and transactional data to identify potential suspicious items and corresponding risk exposure. The solution should have the following three key functional areas adequately combat check fraud:
- Transaction Analysis—Process debits and credits contained in deposits and withdrawals and identify suspicious items, such as out-of-range check numbers and check amounts and duplicate check numbers. A solution should also apply tests at the account and entity level, measuring such things as account velocity, account volume, and deposits or withdrawals of unusual amounts.
- Check Stock Validation—Analyze presented check images against historical, referenced check images, validating the consistency and accuracy of check stock. The solution should effectively identify counterfeit in-clearing and over-the-counter checks with greater speed, accuracy, and reliability than visual inspections.
- Signature Verification—Use machine learning algorithms and sophisticated decision trees to provide a detailed analysis of check signatures. This results in efficient evaluation of suspect in-clearing and over-the-counter checks and increased confidence levels for acceptance and return decisions. The solution should also compare digitized signatures to referenced images, manage multiple signatories on the same account, and monitor items requiring dual signatures to validate check signatures on personal and business accounts. Focusing on dynamic aspects of the signing action, including signature fragments, handwriting trajectories, and geometric analytics, help produce confidence scoring based on these aspects when comparing newly‑presented check signatures with previously saved images to determine matching and nonmatching elements.
The ARGO Fraud solution, OASIS™ (Optimized Assessment of Suspicious Items), provides cross-channel, multi-fund analytics and adjudication workflow to detect fraudulent transactions and suspicious items. It has the highest accuracy and capability in the industry for detecting check and deposit fraud for counterfeits, alterations, forged-maker signatures, on‑us items, and transit items during deposit, as well as kiting and other internal fraud scenarios. It analyzes images of items deposited as well as characteristics of the account, entity, conductor, channel, and so forth.
For more information, download the “Fraud & AML Solution Overview” interview with David Engebos, President and COO of ARGO.