Articles

Top Use Cases of Intelligent Document Processing

Top use cases of intelligent document processing

Currently, most enterprises have a workflow rampant with manual document-heavy processing. 

However, businesses are quickly digitizing their document-processing workflows. 50% of B2B invoices across the globe will be processed without manual intervention according to a Gartner study. The reason? Manual document processing is more expensive than the cost of the documents themselves. 

For example, the average cost of processing a single invoice was $10.89 in 2021. Manual document processing is also prone to human errors like fat finger errors. In a world where 90% of the data is unstructured, you need a tool that can automatically convert unstructured data into structured data to supercharge your productivity. 

This guide explains how you can use intelligent document processing to save your business plenty of money, time, and resources. 

What is Intelligent Document Processing?

Intelligent Document Processing (IDP) is a technology that automatically extracts unstructured data from multiple document sources, including images, online forms, and PDFs. IDP is also known as Cognitive Document Processing (CDP). 

IDP converts this unstructured data into structured data using multiple technologies, including natural language processing (NLP), machine learning (ML), optical character recognition (OCR), and intelligent character recognition (ICR). Together, these technologies make IDP intelligent.

OCR is often used interchangeably with IDP. However, that’s not true. IDP uses OCR as one of the technologies to extract data. 

How Does Intelligent Document Processing Work? 

Here’s how a document is processed using IDP: 

  • Conversion: An IDP platform starts by capturing your document through a scanning device. Once it converts a physical document into a digital one, it starts ingesting data. 
  • Document image processing: The document’s image is processed for optimal OCR and archival. 
  • Reading text using OCR: OCR helps the machine accurately read the scanned document’s text. 
  • Identify language elements with NLP: IDP platforms use NLP to find language elements using methods like feature-based tagging and sentiment analysis. 
  • Machine learning algorithm classifies information: A combination of machine learning and other techniques is used to classify the information in the document. 
  • Extracting elements using AI: IDP uses AI to extract information elements like contact numbers, addresses, and names. 
  • Validation: IDP platforms validate information using third-party databases and lexicons for data validation. Data points are flagged when the platform can’t validate them so someone from the team can review them manually. 

Top Intelligent Data Processing Use Cases in Banking 

Reading and writing financial documents make up a large portion of a bank’s workflow. As a bank, you need to process data fast to offer best-in-class services to your customers without making errors. 

IDP helps banks guarantee accuracy and efficiency to their clients. In addition to data extraction’s key role in a bank’s workflow, banks can also use IDP platforms for fraud detection. 

Here are some of the most common use cases of IDP for banks. 

Mortgage Underwriting 

Customer satisfaction with mortgage originators reduced by five points on a 1,000-point scale in 2021 according to a study by J.D. Power driven by record mortgage origination volume. Banks need to automate their mortgage workflow to scale as the demand grows. After all, customer satisfaction is one of the most significant differentiators in the mortgage industry. 

The mortgage workflow involves collecting various documents. Extracting data from these documents is one of the major factors slowing down the workflow. This is where an IDP tool can help streamline your mortgage workflow. 

An IDP tool helps you speed up the underwriting process with automation. It automatically reads and extracts relevant data and relays it to your bank’s credit evaluation system. 

Claims Processing

The P&C Customer Satisfaction Survey reveals that the claim filing process is the biggest driver of customer satisfaction. 

However, the claims processing workflow can be complex. Claims data comes in various formats—customers might send data as word files, PDFs, and images. Plus, you might receive the data via multiple channels—you might receive it via email, chat, or over a call. 

Unifying this data without manual effort is a massive challenge. Traditionally, banks used OCR to process physical documents. However, the lack of accuracy required manual review. 

An IDP tool is a great alternative to OCR for claims processing. Thanks to technologies like NLP, computer vision, and deep learning, it provides greater accuracy than traditional OCR. 

Customer Onboarding 

Customer onboarding is one of the most resource-intensive processes for a bank. Banks spend an average of $280 to onboard a single client according to Backbase—the cost can add up when you’re onboarding hundreds or thousands of customers every month. 

Many of these expenses go towards processing documents, including the bank’s forms, credit reports, or tax returns. Sure, you can try automating this workflow. However, the automation will break down as soon as a new document type is introduced or you change your form’s template. 

An IDP tool can help tame your customer onboarding costs. Your customers will appreciate a fast onboarding experience, and you’ll save money, increase productivity, and make an excellent first impression. 

Financial Document Analysis 

Banks handle thousands of financial documents every day. From financial statements to tax returns, carefully studying financial documents is critical to a bank’s operations. 

Financial analysis is a cognitively heavy task. Why make your team spend time on mundane tasks like manipulating data when you can use an IDP tool to automate this process and enable your team to concentrate on their more complex deliverables. 

Using an IDP tool helps analysts automatically structure and populate relevant financial data into their system. You’ll do your analyst team a favor by eliminating a lot of their manual work, allowing them to focus on analysis. 

KYC Process Automation 

KYC (Know Your Customer), Re-KYC, and C-KYC are critical for compliance. Banks might need to refer to a customer’s KYC details at various stages during a customer’s journey. 

However, handling hand-written KYC forms is a hassle. Migrating a customer’s KYC data comes with challenges like human error and work overload. Committing errors when underwriting a mortgage or onboarding a customer costs money, but failing to comply with KYC requirements may increase the legal, compliance and regulatory risks.

Using IDP ensures accuracy, so you never have to lose your reputation and pay a fine for failing to comply with KYC norms.  The McKinsey KYC Benchmark Survey found that by increasing end-to-end KYC-process automation by 20%, an organization could enjoy the following positive outcomes: 

  • Increased quality assurance by 13% 
  • Improved customer experience (by reducing customer outreach frequency) by 18% 
  • Increased the number of cases processed per month by 48%

 

The Bottom Line 

Banks process a colossal amountnumber of documents and data each day. Getting new customer data into the system, processing claims, and analyzing financial statements are heavily data-driven tasks that involve dozens of documents from hundreds of customers. 

The probability of committing errors is high. Banks also need a large team just to process documents and structure the data in those documents. 

Banks need an IDP tool to automate this process and remove the risk of error from the process. It also integrates with applications to make migrating the data easier. An IDP tool also validates data and alerts team members in exception cases, when it requires a human to review accuracy. 

It is important to select an IDP tool that offers the right solutions for your industry. Better yet, find a partner who can create a custom IDP solution tailor-made for you. 

Why Choose Blanc Labs Intelligent Document Processing? 

Blanc Labs partners with financial organizations like banks, credit unions, and fintechs to automate operations. 

We can help you create robust automation solutions that minimize manual effort, reduce errors, and improve productivity. Our team helps you use the most advanced technologies including AI and ML to automate complex, resource-heavy processes like document processing. 

Book a discovery call with us if your financial organization deals with plenty of documents daily. We’ll come up with a tailor-made solution to minimize the friction in your document processing workflow. 

 

News

thirdstream and Blanc Labs collaborating to bring intelligent document processing to financial institutions

Document understanding and data extraction are keys to accelerating account opening and supporting underwriting of new retail and commercial accounts.

thirdstream, a leading provider of retail, commercial and credit card onboarding services, deployed with over 40 Canadian financial institutions, today announced a partnership with Blanc Labs, a trusted technology innovation partner to leading financial institutions. The collaboration injects Blanc Labs’ Intelligent Document Automation (IDA) onto thirdstream’s platform, extending existing services to include a proven solution that removes up to 80% of manual document reviews, thereby improving the customer and member experience.

“Our goal is to help our clients continually improve the experience for applicants and account holders. Our partnership with Blanc Labs leverages our Platform-as-a-Service, where our clients will be able to spin up the services Blanc Labs has already deployed with leading financial institutions, reducing the reliance on employee reviews of documentation,” said CEO Keith Ginter. “For those already using the thirdstream platform as part of their onboarding process, Blanc Labs’ Intelligent Document Automation (IDA) helps remove up to 80% of the manual document reviews and results in considerable improvement of the customer experience.”

Automated document understanding and data extraction are some of the keys to moving faster, especially when onboarding new commercial deposits and retail lending customers. thirdstream and Blanc Labs present a structured series of steps to deliver starting with the moment of customer engagement to data extraction using artificial intelligence  from each page of documentation. This eliminates the need for the manual entry of data, with complete and accurate data presented as part of the decisioning and account creation experience.

“Our services today address challenges across the financial ecosystem. Together with thirdstream, we’d like to offer faster time to value realization with our solution. Blanc Labs’ Intelligent Document Automation eliminates manual intervention and creates a compelling value proposition for banks, financial services, and insurance institutions. By increasing operational efficiencies, banks can focus on creating additional revenue streams and provide greater value for the end customer,” says Hamid Akbari, Blanc Labs’ CEO.

thirdstream and Blanc Labs help financial institutions deploy new products and services faster – a key consideration in today’s economy – as they build improved personalized services at scale. Our solution benefits financial institutions looking for pre-integrated innovative solutions that can de-risk and accelerate their modernization and digital transformation efforts.

About thirdstream

thirdstream is headquartered in Lethbridge, Alberta, providing digital account opening solutions, online and in-branch, to over forty Canadian banks, credit unions and trust companies. From identity verification to account funding, thirdstream’s solutions support consumer and business account opening, credit card onboarding, and unsecured retail lending, including adjudication. The thirdstream platform is cloud-deployed, designed for retail and business consumers seeking out financial institutions, and for financial institutions targeting consumers anywhere, any time, from any device. To learn more, visit www.thirdstream.ca.

About Blanc Labs

Blanc Labs is a preferred partner for enterprises looking to digitize and build the next generation of technology products and services. To help companies rapidly deliver on their digital initiatives, Blanc Labs has developed expertise and bespoke solutions in a wide variety of applications in financial services, healthcare, enterprise productivity, and customer experience. Headquartered in Toronto, Blanc Labs serves the Americas through operations in Toronto, New York, Bogota, and Buenos Aires. For more information on how Blanc Labs is building a better future, visit www.blanclabs.com.

Articles

How Canada’s largest independent brokerage used Blanc Labs’ expertise in Intelligent Document Processing to speed up their time to market

Canada’s largest independent online brokerage had an aggressive target date to launch and debut its residential mortgage product to originate loans through an in-house, proprietary Point of Sale (POS) software application. The POS solution needed to collect loan application data and documents from the borrower and co-borrowers.

The challenge was to buy or build the document automation layer of the solution in a short period of time.The online brokerage had limited internal resources to build the solution and needed a technology partner with experience in building digital lending products. The chosen partner needed to either bring its own intellectual property or build/integrate with required FinTech components.

Blanc Labs’ Expertise In the Canadian Mortgage Industry and Intelligent Document Processing

Ultimately, the online brokerage chose to leverage Blanc Labs’ expertise in the Canadian mortgage industry and intelligent document processing in order to collaborate on the design of a total solution and the development of its components.

Apart from achieving the technical and functional feature set defined for the online brokerage’s document automation, the project resulted in:

  • Accelerated time to market
  • Lower Cost of Ownership
  • Futureproof Technology Architecture
  • Better User Experience
  • Enterprise Level Document Management

Want to know how? Download the case study!

Articles

Three Reasons Financial Institutions Are Losing Out to FinTechs

…And How to Keep Up with Digital Natives 

by Bob Paajanen and Charles Payne

Reasons why Banks and Losing Out to Fintechs

The way we bank has changed forever. While FinTechs have the latest technology innovations, what they don’t have is decades-worth of relationships with customers and large swaths of Big Data. Financial institutions need to recognize this advantage, leverage their data, streamline processes, and thereby empower their relationship managers if they want to compete with their new-age rivals.  

Mismanagement of Data 

Most financial institutions have multiple customer-facing systems that operate in their own silos. As many as 50% of banks and credit unions state that they have trouble accessing their internal data. Without a single unified view of their customer, banks and credit unions are unable to collect, process, or indeed deploy insights that will enable them to cross-sell products and services to their customers. 

The services gap left by financial institutions is especially felt in commercial banking where FinTechs are sweeping up SMBs with targeted products and quicker access to funds. A prominent example of this trend is Shopify, which started out as an e-commerce platform, but is now the tenth-largest provider of financial services to SMBs. Another example is Stripe, which has created an end-to-end lending API (application program interface) as its next offer to SMBs. 

Paper-heavy processes, and disparate data management systems are some of the major causes of this issue. As the finance industry moves toward open banking, it is imperative that financial institutions unlock the value of their data and translate it into actionable insights so they can improve their languishing businesses.  

why financial institutions are losing out to fintechs
Source: 11:FS ‘Fintech filling services gaps’ Designing digital financial services that work for US SMBs 

Lack of Efficiency 

A 2019 Gartner report estimated that process automation, including document processing, could save financial institutions 25,000 hours of avoidable work per year. With advances in technology in the last three years, it is not hard to imagine that this number may have gone up even further.  

Most of the productivity loss mentioned above has been attributed to human error. This is hardly surprising when many financial institutions continue to use paper-heavy loan origination models. Without automation, document processing is rife with efficiency and security issues including document mishandling, collaboration on email (generating multiple copies of the same document), versioning issues, loss of time to find the documents when required, a lack of compliance, and a lack of remote access. 

Since the pandemic, consumer expectations have changed dramatically. Close to 60% of customers today are open to completing their mortgage applications entirely online without support on the phone or in person. Even more pressing than the platform, is the need for speed, with customer satisfaction falling 15 percentage points for approvals that take longer than 10 days.  

With unprecedented demand for mortgages, financial institutions must speed up intake, underwriting and decisioning processes faster if they want to keep the customer’s business. 

Costs  

Inefficient loan origination processes lead to rising costs. On average, loan origination costs $7-9k per application. That is over and above the cost of productivity loss, estimated to be $878,000 (for 25,000 hours lost per year) for a company with a 40-person finance team. This cost is invariably passed on to the customer who may end up paying higher fees and charges compared to what they might pay if they opted for a non-banking entity.  

rising cost of loan origination

The FinTechs Are Coming… And how to slow them down 

As a result of service gaps and inefficiencies, customers from both commercial and retail banking have been veering towards nonbanking entities for loans. 50% of Canadian SMBs in 2021 felt that they couldn’t maintain their growth strategies “due to a lack of capital.” Today, nonbanking entities, account for more than 70% of total originations. By using automated processes and digital interfaces, non-banking entities or FinTechs are 25% cheaper than the industry average and can deliver a decision 30% faster compared to other financial entities.  

In the age of Open Banking, it is important that financial institutions update their legacy processes and unlock the potential of their data if they want to survive.  

The automation journey begins with intelligent document processing. Blanc Labs provides a 360-degree IDP (Intelligent Document Processing) solution that can:  

  • Automate workflows for document collection, digitization, and analysis 
  • Replace manual effort through intelligent data capture 
  • Connect with third party data providers for analysis and insights 
  • Analyze document data, provide status alerts, and flag fraudulent entries 
  • Secure documents in a drop box 
  • Deploy on-premises, in the cloud, or as a hybrid model 

Book a demo or discovery session with Blanc Labs to learn about the impact of our IDP solutions for banking.  

 

Articles

Why Banks Need Intelligent Document Processing

By Charles Payne and Donald Geerts 

Why banks need intelligent document processing

In the last two years, we have witnessed a consumer engagement revolution. The pandemic has seen a rush toward digital channels in all facets of life, including the banking industry. The need for instant gratification and round-the-clock support means that lenders must process customer or broker requests faster while balancing security, compliance, and risk management. Data released by the Canada Mortgage and Housing Corporation (CMHC) suggests that in the first half of 2021, the mortgage industry in Canada saw its fastest growth in the last 10 years. Given the rising demand of the market, the “need for speed” in the loan origination and decisioning process is at the top of the list.   

Staying ahead of the competition requires a digital transformation that often begins with intelligent document processing as the first step. Financial institutions must partner with the right intelligent document processing (IDP) solution provider that will deliver both speed and accuracy to meet consumer expectations.  

why banks need intelligent document processing

Tedious and time-consuming processes 

The process of mortgage approval or renewal involves many, many documents. Before a mortgage is even approved, a mobile mortgage lender must collect and organize documents (sometimes handwritten), send them to various personnel in the financial organization to be vetted, and finally return to the customer with a yes or no—a process that can take up days or weeks. If a bank takes too long to respond to a borrower, they may turn to offers from other lenders. Such a situation is easily avoided with the help of intelligent document processing. Once a document is received, the right IDP program can classify it, extract data from the document, and store the data in a way that is accessible around the clock, not just to employees of the lender but to RPA (robotic process automation) processes as well. If additional documents are required, the RPA process can notify the mortgage agent or borrower. If the application is complete, then the RPA can send the data ahead for auto-decisioning. Using IDP in combination with RPA can ensure a quick turnaround on an application without consuming too much time. 

Organizations with no digital document processing reported 10x more at-risk customers and 2x more at-risk revenue compared to other companies. (Forrester, 2020) 

Inability to scale 

One way to address the growing demand for mortgages is to hire, train and retain more employees. However, increasing the size of the team may result in a higher time to value (as new employees will take time to ramp up to desired levels of efficiency) and increased costs too. Lenders can benefit from IDP solutions that may be scaled up quickly with a marginal infrastructure cost.  

Just digitization isn’t enough 

Many lenders today receive applications through mortgage portals. While the first step of digitization of documents is taken care of, banks do not follow through to ensure the proper classification, extraction, and storage of these documents. As a result, an employee must still go through the documents to verify and authenticate their contents to ensure they are adequate for an application. It is no surprise that knowledge workers lose 50% of their time preparing documents and therefore, experience a 21% loss in productivity because of document issues.  

Security and risks 

Worldwide, the digital fraud attempt rate grew by 52.2% in 2021 compared to two years earlier. Banks or financial institutions that do not have intelligent document processing capabilities may be caught off guard or may not be able to respond in time to stop transactions. IDP, on the other hand, can reduce the incidence of fraudulent transactions by assessing large volumes of historical data accurately and in real-time. By identifying the patterns, an automated system can immediately flag a suspicious transaction and stop it if necessary.  

KYC is another area where IDP software can help by minimizing human error. The IDP program can read submitted documents, verify the identity and details of the customer by searching through data repositories and even assign them a risk score, thereby helping the lenders meet regulatory standards.  

Unaligned with consumer demands 

Unsatisfactory products and fees, slow response to problem resolution, and a lack of convenience are some of the top reasons why financial institutions are are losing out to FinTechs and digital-only banks. One of the biggest contributions IDP can make is to automate repetitive manual tasks and free up lenders employees’ time in activities that will increase customer satisfaction—building trust & rapport and enhancing product offerings.  

Automate document processing with Blanc Labs 

There are many reasons why banks need intelligent document processing, and Blanc Labs provides a 360-degree IDP solution that can:  

  • Automate workflows for document collection, digitization and analysis 
  • Replace manual effort through intelligent data capture
  • Connect with third party data providers for analysis and insights 
  • Analyze document data, provide status alerts, and flag fraudulent entries 
  • Secure documents in a drop box 
  • Deploy on premises, in the cloud or as a hybrid model 

 

Book a demo or discovery session with Blanc Labs to learn about the impact of our IDP solutions for banking.  

Articles

Extraction: The Next Step in Intelligent Document Processing  

By Luciano Lera Bossi, Alejandro Nava and Parsa Morsal  

intelligent document processing extraction

One of the starting points of digital transformation, especially for financial institutions, is intelligent document processing or IDP. We previously explored classification as the first step in IDP. In this article, we will explore the next crucial step, extraction.   

What is document extraction?  

Document data extraction is a process of extracting data from structured or unstructured documents and converting them into usable data. It is also called intelligent data capture. With the rapid progress in document imaging technology such as the incorporation of natural language processing (NLP) and optical character recognition (OCR) as well as advanced analytics, we can now enable IT systems to understand the data that was thus far only on paper.  

Powered by machine learning models and NLP, IDP systems can now bring the benefits of AI to document processing. The intelligence and detail offered by IDP systems today can be used for many functions including compliance and fraud. The level of granularity, accuracy, and speed offered by IDP systems today, can hugely impact the scale of digital transformation for your organization.  

Document processing and the banking industry  

The financial industry is no stranger to the benefits of IDP. In a recent study of 200 banks in the US, it was found that 66% of the respondents eliminated the need for manual processes for a typically labor-intensive industry thanks to IDP; and 87% cited accuracy and extraction as the key reasons for incorporating IDP into their systems. Given the emphasis on accuracy and extraction, it is important to understand how intelligent document processing coupled with OCR and NLP can give desired results.

OCR vs IDP

OCR as a document processing technology has been around the longest. OCR is used to extract handwritten or typed text in documents which can then be converted into data. While OCR has been synonymous with data extraction for many years, it is not without its challenges. Without intelligent processing of the data in understanding what the data is for, OCR may give inaccurate results. There can be errors in detecting a text block in an image (error in word detection), there may be errors in interpreting words correctly if there are differences in text alignment or spacing (error in word segmentation) or there may be errors in identifying a character bound in a character image (error in character recognition).   

However, when combined with intelligent processes such as NLP and machine learning analytics, time-intensive processing tasks can be sped up with minimal errors. The biggest differentiator between OCR and IDP is that IDP can also handle documents that may be structured, semi-structured, or unstructured.

Structured Documents  

Structured documents generally focus on collecting information in a precise format, guiding the person who is filling them with precise areas where each piece of data needs to be entered.  These come in a fixed form and are generally called forms. Examples of structured documents include tax forms and credit reports.   

Semi-structured Documents  

Semi-structured documents are documents that do not follow a strict format the way structured forms do and are not bound to specified data fields.  These don’t have a fixed form but follow a common enough format.  They may contain paragraphs as well. Example of semi-structured documents could be employment contracts or gift letters.  

Unstructured Documents  

Unstructured documents are documents in which the information isn’t organized according to a clear, structured model. These files are all easily comprehensible by human beings, yet much more difficult for a robot. Examples of unstructured documents include mortgage commitment statements and municipal tax forms.   

Textual and Visual data extraction in IDP  

The two main aspects that efficient IDP solutions tackle are textual data extraction and visual data extraction. In textual data extraction, the entity extraction technique is applied to recognize text in a document. This is a machine learning approach where the software is exposed to thousands of documents and the machine “learns” to identify information and segregate it based on certain semantic parameters. Entity extraction can involve a variety of tools and techniques including neural networks to visual layout understanding. By using entity extraction methods, you can avoid going down the template route and thereby use the software on various kinds of documents.   

In visual data extraction, IDP solutions can be designed to understand elements such as signatures, tables, checkboxes, logos, etc. Visual data extraction is more complex than textual data extraction as it involves detecting, analyzing, and extracting information from the regions with visual elements accurately while also denoising content that is not relevant. Using machine learning, advanced visual extraction models can also understand the structural relationship of the visual data and its relevance.   

Choosing the right IDP solution that can handle both text and visual elements accurately across varying document types will ensure that there is no need for your back office to comb through documents once again.   

Explore Kapti, our intelligent document processing software to find out how the power of machine learning and automated document workflows can transform your organization’s document processing experience.  

  

Interested in hearing how we can accelerate your digital transformation?