Want to see these new features in action? Schedule a demo with an expert from our team today!
Do you remember the first time you applied for a credit card? Or took out a loan for your business?
Maybe you’ve waited three or even six months to get approved for that SBA loan. Or perhaps you were denied on the credit application because you’re one of the millions of consumers without a credit score.
We’ve all suffered from unfair or inefficient processes in our interactions with financial institutions. And the cost isn’t just an expense for financial service companies — it’s an expense for customers as well.
Take credit scores, for example: In addition to the 26 million Americans who are considered “credit invisible” due to a lack of any credit history, one in five Americans (approximately 62 million) are considered “thin file” with fewer than five credit accounts. These “thin-file” and “credit invisible” consumers (along with non-U.S. residents and other underserved communities) are prevented from accessing financial products due to the barrier of credit scores.
On top of that, the increasing popularity of “Buy Now, Pay Later” services can negatively impact credit scores even if on-time payments are made. And even just this year, we’ve seen that a simple computer coding error can incorrectly affect credit scores, preventing consumers from accessing vital financial products like credit cards and loans.
To address this, financial institutions need to ask what they can do differently to assess fraud and credit risks earlier and more effectively. Most organizations have access to vast amounts of data that can be used to inform lending decisions (tax documents, bank statements, pay stubs, etc.); a large amount of that is just trapped in documents.
A robust data strategy is what will help stop the financial services industry from lending money to the wrong entities. For companies that can master this, fraud and credit risk management will be a strategic differentiator.
Already in 2022, Inscribe has seen substantial growth and progress toward our mission of creating a fair and efficient financial services ecosystem: Not only have we surpassed a 3x year-over-year increase in annual recurring revenue, but we are now processing 4x more documents each month than we were in 2021.
Documents are not just central to most financial crimes — they are a critical component of all financial decisions.
Inside those documents are millions of data points and limitless possibilities. Our customers span across a multitude of use cases and industries, and each document we process enhances the significant amount of intelligence in our AI and machine learning algorithms — which is what enables Inscribe to surpass other fraud and automation tools available to financial services organizations today.
Many document fraud detection solutions currently on the market utilize a “human-in-the-loop” approach, where the documents are being manually reviewed by teams of people who don’t work for the financial institution (essentially, outsourced strangers). This means that those organizations wait hours for results. In addition, our customers have told us that some document automation solutions will return documents with only a “failed” result, no parsed data points, and no insights as to why.
These are not the data-driven insights that modern organizations require to grow.
We believe automating document reviews is safer and faster when the only humans in the loop are the team making application decisions. Our AI models trained on those billions of data points can return results in seconds, provide fraud insights that could never be detected with the human eye, and keep sensitive data safe.
And today we’re excited to introduce new Credit Analysis™ and bank statement automation features from Inscribe that give companies instant access to the vast amount of financial data contained within documents so that they can make faster and more inclusive lending decisions.
In the past, risk and operations teams had to spend upwards of 30 minutes manually reviewing a single application document for information. Building a solution internally would cost them time and internal resources (as well as limit the data available for machine learning models), and existing solutions on the market often require hours to analyze documents.
New Credit Analysis™ and advanced automation features from Inscribe provide an almost instant snapshot of important data points needed to make lending decisions with confidence — including cash flow details from bank statements, transaction parsing, and pay stub parsing. Inscribe accurately extracts and these returns key details (names, addresses, dates, transactions, salary) in just seconds.
Inscribe’s new Credit Analysis™ snapshots give risk and operations teams a summary of key bank statement details to help you quickly determine an applicant’s creditworthiness. The snapshot includes the number of days with a negative balance, minimum balance, average daily balance, total net, total gross debits, total count of debits, total gross credits, and total count of credits. This makes it possible to provide fast and near-frictionless experiences that outperform competitors.
We’ve gotten some great feedback from our customers about this feature already:
Inscribe’s new transaction parsing feature digitizes bank statement transactions in just seconds and provides you with the date, description, and amount for every transaction. This makes cashflow analysis so much easier, allowing teams to evolve their underwriting processes and make lending more inclusive. Plus, it’ll make manual reviewers happy too.
How do our customers know that transactions have been parsed correctly? Inscribe provides a single confidence score for all the transactions provided in a document. This score is calculated on a scale of 0 - 1 and reflects Inscribe's confidence that the transactions have been parsed correctly. This eliminates any uncertainty around the results. Even if the confidence score is low, Inscribe will still return partially parsed data.
The confidence score can also be used to automate the transaction results via our decision engine and determine when they want to conduct a manual review. Fast-growing fintechs like Ramp use transaction parsing to reliably automate their application review process:
Inscribe’s new pay stub parsing feature digitizes pay stubs in just seconds and provides risk and operations teams with the name, address, date, business name, business address, pay period start, pay period end, gross pay for the pay period, net pay for the pay period, gross pay YTD, and net pay YTD. This means their teams no longer have to pull out net pay or annualize income to underwrite loans, which reduces the chance of human error and greatly increases efficiency.
For each of the parsed details in the pay stub provided, Inscribe will also provide a confidence score on a scale of 0 - 1 (which can be utilized within our decision engine to automate the results or set rules for when you’d like to include a manual review).
But don’t have to take it from us. Check out what one of our amazing customers from VIVA Finance says about our parsing:
Bank statement and pay stub reviews cost risk and operations teams too many hours each week and prevent them from providing fast approvals. Today's most successful financial services are technology-driven, creating new customer experiences that are transparent and frictionless. So when our customers told us that they needed a way to automate those reviews without increasing fraud or credit risk, we listened.
We’re thrilled to continue innovating for our customers and fulfilling our mission of creating a more fair and efficient financial services ecosystem.
Want to see these new Credit Analysis™ and advanced automation features in action? Reach out to speak with one of our experts today.