This article was written by Greg Council and first published on August 15, 2016 in the IBM ECM Blog and an excerpt is provided below:
Signatures are a unique biometric that belongs to each individual. Banks, businesses and governments rely on signatures to verify identification and authorize transactions. While a number of technologies and solutions have come to the market to obviate the need for traditional “wet ink” signatures, they are still the most common way to complete legal documents of all types from checks and wire transfers to contracts. There is still a lot of cost associated with ensuring that the signature on that document is from the actual person authorized to sign it. The costs all come down to the variance of the signature itself along with the enormous volume of signatures to verify.
What Happens with All Those Signatures
Do you ever wonder what happens to signatures on the checks or other documents you sign? On two different days your signature, although genuine, might look very different. So why don’t you ever get a call from the bank asking to confirm a transaction?
There are a number of reasons, but one might be that their signature analysts understand that there’s a certain amount of variability between genuine signatures. Another could be that the dollar amount was under a threshold and that your signature was never reviewed. After all, most organizations can’t affordably staff for the number of signatures going through the system at any given time, so they focus on higher-risk items. Unfortunately, this can lead to problems.
There are many well-known examples of fraudulent transactions that were conducted simply through forging a signature. One recent example is a large real-estate scandal that involved fake documents with forged notary signatures resulting in over $2M in illicit proceeds. In another case, a New Jersey man forged the signature of a New York Mets executive to obtain $3.5M in financing. So, it’s clear that signature verification hasn’t reached the necessary level of use.
Signature Verification Automation
Signature verification software can play a valuable role here. Not only can it process more documents (meaning ALL checks or other documents can be , but for processing large volumes of documents, it can do so more accurately than humans.
The whole automated verification process can be compared to the work of a group of highly skilled experts. Each of them has a favorite approach, looking at particular characteristics, which is especially efficient in some cases and “good-enough” in others. When they work together as a team, their areas of expertise complement each other, which results in excellent overall performance.
However, this is not a call to eliminate humans from the equation. After all, human scrutiny nicely complements the steady, unwavering predictability of software algorithms. To minimize fraud detection, the best mix involves both software verification and human exception-handling, which reviews signatures when the software reports lower confidence levels.
Signature verification software is fast, accurate and consistent, and has proven to outperform humans on even the most difficult types of forgery. This Signature Verification Infographic highlights key characteristics of signatures that are compared, along with different comparison methods.
Download the Parascript White Paper to understand the different types and benefits of automated signature verification as well as compare online and offline signature verification techniques.