Ocrolus Debuts AI-Powered Document Analyzer Instant

Document automation firm Ocrolus has debuted Instant, its automated document processor.

Instant, announced Wednesday (Sept. 20), is an artificial intelligence (AI)-powered service that lets lenders analyze bank statements and other financial documents for faster lending decisions while reducing risk.

“Ocrolus has analyzed hundreds of millions of pages of financial documents, using AI working in tandem with Human-in-the-Loop (HITL) data validation,” Sam Bobley, Ocrolus’ co-founder and CEO, said in a news release. 

“Thanks to our massive volume of training data, our automation capabilities have reached a point where we are thrilled to debut a machine-only offering with greater coverage and accuracy than any other software product in the market,” he said. 

According to the release, Ocrolus is offering Instant as a complementary service to its flagship service Complete, which includes human data verification for lower quality documents. 

In an interview with PYMNTS last year, Bobley posited that the finance world had entered a “golden age of automation,” but noted that what “makes us most unique is that we have a human-in-the-loop component to our software.”

The “human loop” begins once Ocrolus examines documents, using automation to read and validate as much information as it can.

“Then any data fields that we can’t automatically confirm we slice into smaller tasks and route through a quality control process where Ocrolus employees perform quality control,” he added, “and then algorithmic checks make sure our workers did the work correctly.”

PYMNTS also looked at some of the ways AI and machine learning (ML) are shaping lending in a conversation earlier this year with LendingClub’s financial health officer, Anuj Nayar.

As that report noted, these technologies can accelerate lending and lay the pathway for instant disbursements, streamlining the entire process. AI-powered algorithms analyze a vast amount of data and other relevant factors in real time, enabling decisions in minutes. 

LendingClub has been using AI and ML in this fashion for quite awhile. The technology can process upwards of 150 billion cells of data and 2,000 different attributes, automating most of the company’s loan approvals and speeding its decisions.

“We can move much faster,” Nayar told PYMNTS. “We’re currently doing a little less than a billion dollars … of loan deliveries, and that takes a lot of sheer technology and manpower to make that stuff happen.”