AGNOSTIC IMAGE DIGITIZER TO DETECT FRAUD

• Main Authors: Odiorne, Mark Alan, Matos, Marcus R, Siekman, James, Albritton, Patricia Ann, Farrar, SR., Aubrey Breon, Khaleeli, Mohamed Faris, Page, Sheila
• Format: Patent
• Language: English
• Published: 01.02.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

Methods for enhancing compatibility of a document of an entity with an organization's database on a computer server to facilitate detection of a fraudulent submission. Methods may include receiving a populated document in a first format from the entity, using a processor to digitize the document into a digital format, such as bytes, and further into a second format, where the first format may not be compatible with the database and the second format may be compatible with the database. Methods may include using the processor, optionally running a statistical model, to determine an entity identifier, a predicted value of a data field in the document, and whether there is a difference between the value in the predicted data field and a corresponding value in the populated document. Methods may include implementing a corrective action, such as raising a fraud alert at the organization, when there is a difference.