Insurance companies have long been awash in documents, for claims processing, underwriting, new customer applications, and more. Now, with digital transformation efforts in full swing, insurers are looking for ways to streamline and automate insurance processes that involve dozens or hundreds of documents. The problem is many of the documents contain unstructured content, making them difficult to deal with for automation approaches that rely on keywords, rule-based methods and templates. Intelligent process automation (IPA), a form of artificial intelligence specifically designed to be able to “read” unstructured documents much like a human does, offers a viable solution that brings immediate value.

Download the Everest Group Whitepaper: Unstructured Data Process Automation

Download Now

Insurance Process Automation Key Benefits

image shows that indico's intelligent process automation can lead to a 4 times increase in process capacity

Capacity Expansion:

Grow revenue without adding expense

image shows that Indico's intelligent process automation can lead to an 85% reduction in process cycle time

Cycle Time Improvements:

Get work done faster

image shows that indico's intelligent process automation can lead to an 80% reduction in the amount of total resources required

Increase Efficiency:

Free up employee time for higher-value work

Knowledge Capture:

Codify and streamline processes

Compete Effectively:

With stalwarts and insuretech startups alike

Customer Satisfaction:

Improve client response time

knowledge workers automating manual document-based workflows

Problems with the Early Attempts at Insurance Process Automation

Documents that contain unstructured content present problems for most insurance companies’ process automation solutions because they are not easily digestible by computers. 

Claims processing, for example, often involves a review of notes from an adjuster based on conversations with the claimant. The adjuster’s notes are largely free-form, following no standard format, with plenty of variation from one adjuster to the next. An adjuster’s file may also include photos, along with reports from doctors and lawyers. In short, it’s a significant amount of content, nearly all of it unstructured.

To process a claim, someone has to pore through hundreds of pages of documents, extract pertinent bits of information and input them to a downstream claims processing system. Relevant data may include the claim number, policy number, date and time of loss, location, coverage limits and more. 

That data entry job is labor-intensive and time-consuming, not to mention error-prone, making it ripe for automation. Companies have tried using insurance process automation tools based on keywords and rules, with less-than-stellar results. 

Keyword and rule-based approaches to insurance automation are developed using templates that define exactly where the data you want to extract is located in a given document, along with a slew of rules defining what data to extract and what to do with it. 

In practice, what often happens is an insurer hires a consulting firm to write countless rules and templates to try to account for every variation in the documents the company needs to process. That may work, briefly – until a document comes along that doesn’t neatly fit into any of the rules or templates the consultants created. Once this happens, the entire system breaks down.

If you think of the example of the insurance adjuster’s notes, it’s easy to see how it won’t take long at all until a new type of document comes along, making the rule-based approach all but futile. On top of that, it’s horrifically costly, whether you use outside consultants or in-house resources. 

Documents that contain unstructured content present problems for most insurance companies’ process automation solutions because they are not easily digestible by computers. 

Claims processing, for example, often involves a review of notes from an adjuster based on conversations with the claimant. The adjuster’s notes are largely free-form, following no standard format, with plenty of variation from one adjuster to the next. An adjuster’s file may also include photos, along with reports from doctors and lawyers. In short, it’s a significant amount of content, nearly all of it unstructured.

To process a claim, someone has to pore through hundreds of pages of documents, extract pertinent bits of information and input them to a downstream claims processing system. Relevant data may include the claim number, policy number, date and time of loss, location, coverage limits and more. 

That data entry job is labor-intensive and time-consuming, not to mention error-prone, making it ripe for automation. Companies have tried using insurance process automation tools based on keywords and rules, with less-than-stellar results. 

Keyword and rule-based approaches to insurance automation are developed using templates that define exactly where the data you want to extract is located in a given document, along with a slew of rules defining what data to extract and what to do with it. 

In practice, what often happens is an insurer hires a consulting firm to write countless rules and templates to try to account for every variation in the documents the company needs to process. That may work, briefly – until a document comes along that doesn’t neatly fit into any of the rules or templates the consultants created. Once this happens, the entire system breaks down.

If you think of the example of the insurance adjuster’s notes, it’s easy to see how it won’t take long at all until a new type of document comes along, making the rule-based approach all but futile. On top of that, it’s horrifically costly, whether you use outside consultants or in-house resources. 

What About OCR and RPA?

It’s not unusual to hear about optical character recognition (OCR) as a solution for intelligent document processing in insurance claims and other processes. But by itself OCR can’t effectively deal with the unstructured content that is the hallmark of insurance documents.

OCR is machine learning technology that can be used to convert documents such as PDFs into a machine-readable format. That’s useful, but it still leaves you dealing with templates to actually extract useful information, and all the issues that presents.

Robotic process automation in the insurance industry suffers from much the same problem when it comes to these types of use cases.

There are a number of RPA use cases in insurance. RPA is great at automating processes that involve the exact same steps each time. Say, for instance, an insurance data entry clerk entered the exact same keystrokes in the same order time after time into a claims processing system. That would be a process that’s ripe for automation using RPA.

But, as explained above, that’s not at all how the process works. Rather, it requires a human being to make judgment calls about which data to extract and enter. Any insurance process that involves unstructured documents – which is most of them – will suffer the same problem. (RPA can, however, complement IPA in an insurance automation solution. More on that here.)

It’s not unusual to hear about optical character recognition (OCR) as a solution for intelligent document processing in insurance claims and other processes. But by itself OCR can’t effectively deal with the unstructured content that is the hallmark of insurance documents.

OCR is machine learning technology that can be used to convert documents such as PDFs into a machine-readable format. That’s useful, but it still leaves you dealing with templates to actually extract useful information, and all the issues that presents.

Robotic process automation in the insurance industry suffers from much the same problem when it comes to these types of use cases.

There are a number of RPA use cases in insurance. RPA is great at automating processes that involve the exact same steps each time. Say, for instance, an insurance data entry clerk entered the exact same keystrokes in the same order time after time into a claims processing system. That would be a process that’s ripe for automation using RPA.

But, as explained above, that’s not at all how the process works. Rather, it requires a human being to make judgment calls about which data to extract and enter. Any insurance process that involves unstructured documents – which is most of them – will suffer the same problem. (RPA can, however, complement IPA in an insurance automation solution. More on that here.)

Insurance Process Automation with IPA

Intelligent document processing technology, as implemented by Indico, is fundamentally different from RPA and templated approaches because IPA can understand document context much like a human does. That’s because it’s based on a model that incorporates some 500 million labeled data points, enough to enable it to understand human language and context. 

Having a large set of data to “train” on is what brings intelligence to any artificial intelligence solution. But to utilize AI in insurance, even the largest insurance companies would be hard-pressed to create their own model based on that much data.

Indico then applies technology known as transfer learning to create custom models that can tackle virtually any downstream task – including claims automation and other common insurance automation use cases. The end result is insurance companies can automate processes using a relatively small number of documents to train the model. What’s more, you don’t need data scientists to make it all work. Rather, the professionals on the front lines train the automation model – those who know the processes best. (For a deeper dive on this point, check out our Intelligent Process Automation page.)

Intelligent document processing technology, as implemented by Indico, is fundamentally different from RPA and templated approaches because IPA can understand document context much like a human does. That’s because it’s based on a model that incorporates some 500 million labeled data points, enough to enable it to understand human language and context. 

Having a large set of data to “train” on is what brings intelligence to any artificial intelligence solution. But to utilize AI in insurance, even the largest insurance companies would be hard-pressed to create their own model based on that much data.

Intelligent Automation in Insurance: Use Cases

IPA can be applied to a number of insurance use cases, including the following four.

Claims Processing

Insurance claims automation is another common use case. Intelligent automation in insurance can be used to automatically classify and annotate a new claim such that it can be effectively routed to the right SME for evaluation and processing. This results in faster turnaround time and improved accuracy for a processed claim, driving improved customer satisfaction and organizational efficiency.

Appraisal Processes

Insurance appraisal processes, whether performed prior to writing a policy to determine property value or after a claim to determine compensation, can involve many unstructured documents. An initial appraisal for property value may include receipts, purchase and sale agreements, and images, while those for claims include contractor estimates and more. An IPA solution can deal with each type of document and help companies automate the extraction of relevant data. This offers another opportunity for insurance document automation.

Commercial Underwriting Processes

Often involving thousands of pages of documentation, major commercial underwriting processes can be dramatically improved by creating underwriting criteria attributes that can automatically be recognized and “scored” using Intelligent Automation, resulting in major reduction in response times when submitting proposals.

Regulatory Compliance

In a highly regulated industry with dozens of state and federal regulatory bodies, responding to regulatory inquiries in a timely manner represents a large expense for most insurance companies. Intelligent Process Automation is able to create augmented responses to inquiries, dramatically reducing the response times and resources required.

Healthcare

Few vertical industries are as document-intensive as healthcare, whether on the provider or insurance side. That makes the healthcare industry ripe for tools that can automate insurance claims processing and other chores, for both providers and insurers alike. Intelligent process automation can help healthcare organisations address unstructured documents driving cost savings and improving the patient experience.

How IPA Complements RPA

Some insurance automation use cases may involve both robotic process automation and intelligent process automation, as the two technologies are complementary.

RPA is great at automating repetitive tasks to make a process less labor-intensive for humans and works well with deterministic business processes that involve structured data. IPA, on the other hand, is able to automate processes that involve unstructured data. 

A common IPA and RPA use case, then, is to use IPA to “read” unstructured content and translate it into a structured format that an RPA tool can then process. For example, the RPA tool may ingest the documents and send them to an IPA tool for classification as well as data extraction. Once extracted, the IPA tool puts the data into a structured format, such as a spreadsheet, that the RPA tool can work with. The RPA tool can then take in the now-structured data and populate a downstream system, such as a customer relationship management (CRM) tool.

Insurance Process Automation: Key Benefits

Keeping up with the pace of business is difficult under any circumstances. But if insurance companies are to achieve digital transformation, it’s imperative. Indico’s intelligent document processing solution can help in that effort while delivering significant benefits, including:

Capacity Expansion:

Automation enables employees to be more productive, so the organization can grow revenue without the expense of increasing headcount.

Cycle time improvements:

Automating manual processes enables companies to get work done faster, even while increasing accuracy.

Increase efficiency:

By automating mundane tasks, you can free up employee time for more rewarding work that’s also more valuable for the company.

Knowledge capture:

Part of the value of an automation exercise is codifying processes that may have existed for years with no formal agreement on how they are supposed to work. At the same time, it’s likely you can streamline processes to make them more effective.

Compete effectively:

It all adds up to making your organization more competitive, putting you on equal footing with the most nimble insuretech startup and largest industry player alike.

Customer Satisfaction:

Customer expectations are at an all-time high. Intelligent automation enables insurers to exceed client demands by improving the speed and accuracy by which they are able to react to customer needs.