Indico Data unveils Indico 6, newest version of their industry leading intelligent intake solution
Read More
  Everest Group IDP
             PEAK Matrix® 2022  
Indico Named as Major Contender and Star Performer in Everest Group's PEAK Matrix® for Intelligent Document Processing (IDP)
Access the Report

Automated Claims Processing for Insurance: A Strategic Guide

Automating insurance claims intake processing

INDICO RESOURCE

F50 Insurance company achieves 300% ROI with Indico Data

Read case study

The ability to efficiently process claims is crucial for commercial insurance, but one that’s traditionally been labor-intensive, involving numerous unstructured documents and images. A solution lies in intelligent claims intake, which applies artificial intelligence to provide automated claims processing for insurance firms and eliminates some 70% of manual claims document handling.

Commercial insurance claims tend to be complex, involving ACORD forms, images, names, dates, and more. And of course, insurers have to confirm the policy is active and the loss is covered, all of which has traditionally required human intervention. But automated insurance claims processing using intelligent document processing dramatically changes the equation, speeding the process by 4x or more.

Simply put, claims automation allows insurers to process more claims faster. That keeps clients happy, increasing client retention. Insurance claims automation also means it takes fewer employees to do the job, freeing up staff for more strategic work.

The claims intake dilemma for insurers: speed vs. accuracy

When it comes to claims processing, commercial insurance companies historically have been forced to choose between speed and accuracy.

Choosing speed means increased risk of errors and non-compliance, making hasty adjudication decisions that can affect profitability, and negatively impacting the customer experience if things go awry.

But choosing accuracy means increasing the risk of losing out to more nimble competitors that offer a faster customer experience, as well as frustrating customers with long settlement times. That, in turn, negatively impacts your net promoter score (NPS), ultimately leading to customers jumping ship.

“Claims dissatisfaction is a major factor in driving policyholders to switch to another company, with 74% of dissatisfied customers either saying they did change providers (26%) or are considering it (48%),” according to a 2022 Accenture study.


Learn how a F50 Insurance company achieves 300% return on investment with Indico Data.

Applying artificial intelligence to insurance claims processing

Intelligent intake platforms mean you no longer have to choose between speed and accuracy. The platforms employ numerous artificial intelligence technologies, including natural language processing, machine learning and transfer learning. Together, these technologies enable employees who actually process claims – such as claims handlers and loss adjusters – to build models to automate claims processing. There’s no need to involve data scientists, or even IT. That delivers a higher level of model accuracy and significant scalability, boosting insurers' ability to roll out automation models across the company.

Integration with insurance automation platforms

Part of the reason intelligent claims intake delivers a 70% reduction in manual document handling for claims is integration with downstream insurance automation platforms such as Guidewire ClaimCenter. Today that’s a familiar swivel chair process, where a claims handler reads a claims email and attachments, looking for data to enter into Guidewire, including case owner, case status number, cause and date of loss, estimates for extent of loss, and the like.

With an intelligent intake solution such as Indico’s, AI models can “read” claim emails and attachments and pre-populate some 80% of the required fields in Guidewire ClaimCenter. This kind of automated claims processing not only dramatically speeds processing time but increases accuracy - because computers don’t get tired and make mistakes like people do. In fact, intelligent intake solutions that support staggered loop machine learning become more accurate over time by learning from when users accept or correct a model’s predictions and classifications.


View Episode 9 of Unstructured Unlocked, where Indico Data’s Christopher Wells talks with Steven Weiss, former Senior Vice President and Chief Underwriting Officer at Munich Re Specialty Group Insurance Service.

Automated claims processing for insurance vs. traditional claims processing

The traditional claims handling process was highly manual. For the initial claims reporting, a client or broker submits a claim by phone or email, triggering a potentially lengthy process to gather all relevant details. This includes collecting documents and images detailing the damage, estimates on repairs, any injury data where applicable, and so on. Often an on-site evaluation is required to assess and determine the validity of the claim, generating potentially hand-written adjuster notes. At some point, a fraud detection process is also initiated, again a highly manual process.

For many years carriers have been trying to automate claims processing by using optical carrier recognition (OCR) technology to help process documents by converting hand-written and printed text to a machine-readable format. While an improvement, OCR required templates to read most documents, making it vulnerable to errors when a given piece of data was not in the exact spot the template expected it to be. That created a costly process of near-constant template maintenance to keep up with new or changed documents. Given that, along with the need for manual review for accuracy, OCR could hardly be considered a solution for insurance claims automation.

Intelligent intake represents a quantum leap forward in insurance claims automation. A form of intelligent document processing, intelligent intake obviates the need for templates. Instead, it uses artificial intelligence technologies, including large language models, natural language processing, machine learning, and transfer learning. Taken together, these technologies enable insurance companies to build intelligent intake models capable of ingesting nearly any kind of document or image and extracting relevant data from it. That data is then converted into a structured format that can be entered into downstream claims processing systems, such as Guidewire Claim Center.

The ability to ingest unstructured documents, extract relevant info from client claims and turn it into a structured format represents a significant step in insurance claim process automation, and gives rise to numerous important capabilities and use cases.

Automating claims processing: Use cases

Claims process automation for insurance can apply to a number of use cases. Following are just a few examples.

Health insurance claims automation
Health insurance claims can be especially complex, with the need to examine potentially extensive patient records. Intelligent intake can greatly speed the process of finding and extracting data from medical records, including not just demographic information, but data such as relevant medical conditions and past treatments that may factor into a claim. Such an automated process saves valuable time for claims handlers, helping them adjudicate health insurance claims far more quickly.

Automated policy verification in claims processing
One of the first steps in the claims process is determining whether the client has a valid policy that covers the claim in question. Intelligent intake enables carriers to quickly extract the claimant’s name, policy number, and type of policy, and convert it to a structured format. Using this data, the carrier can then use robotic process automation to conduct a quick look-up in the policy database to ensure the policy is in good standing.

Auto-adjudication of claims
While all but the simplest commercial claim adjudication will likely involve human oversight, IDP and intelligent intake can help automate numerous steps in the process. They include policy verification, checks for errors and omissions, and pre-populating numerous fields in the claims processing system. With data now in a structured format, it can be entered to any rules-based engines you may use as well as emerging AI claims processing tools that can help further automate the claims decisioning process. All of this saves valuable time in the claims adjudication process, removes much of the drudgery, allows adjusters to focus on the merits of the claim, and gets the client a result much more quickly.

Help with corporate email in-boxes
Chief among the use cases for the automation of insurance claims is the corporate email in-box. It’s common for insurance companies to have a single email address to which clients send claims information that constitute first notice of loss (FNOL).

Many of these emails contain not only potentially complex requests, but attachments, such as ACORD forms, photos showing building or vehicle damage, and the like. Much of this data will be unstructured, making it beyond the scope of a robotic process automation (RPA) solution for claims automation. But an intelligent intake platform can read and triage each email, determining where each should be routed. The platform can also extract attachments, and “read” them to find pertinent data and input it into downstream processing systems such as Guidewire. It adds up to faster insurance claims processing and improved customer satisfaction .

Automating workers’ compensation claims
Any form of claims litigation can be costly for a commercial insurance company, but workers’ compensation claims can be particularly painful because they involve two paper-heavy industries: medical and legal. Medical records can be hundreds of pages long, yet must be examined to comply with subpoenas, legal discovery requirements and the like. Such examinations take extensive resources. But applying intelligent intake technology can ease the burden. With AI models that can reduce manual processing by 70% to 80%, insurance companies can dramatically increase their process capacity, reduce processing timelines, and minimize the need to outsource processing.

Efficiently deal with catastrophe claim surges
Dealing with surges in claim volume following catastrophes such as hurricanes, earthquakes, and floods can severely test any commercial insurance company. Claims that normally take only a day to process can stretch to several weeks amid the high volumes such events prompt.

An intelligent intake solution offers a remedy. Increasing the capacity of an automated claims processing insurance solution is a simple matter of adding compute capacity; easily done in a cloud environment. Given the intelligent intake solution can automate as much as 80% of the process, that leaves only 20% for manual review. Whether that difference is made up with internal employees or third party administrators, it’s a much easier lift at far less expense.

Meet compliance requirements with explainable AI

A key concern in a highly regulated industry like insurance is the ability to explain why an automated, AI-based solution makes the decisions it does. If a claim is rejected, the insurance company must be able to explain in simple terms the reason behind that decision. A sound intelligent intake tool will make that easy, with an audit trail that makes clear – in plain English – the rationale behind each claim decision. Additionally, given insurance claims handlers create the automated models, the AI models naturally reflect the way these professionals think during the claims assessment process.

Read our blog: How intelligent automation speeds up insurance underwriting and claims processing.

Setting the stage for AI-based insurance analytics

Beyond claims handling automation, intelligent intake solutions also set up commercial insurance companies to take full advantage of AI-based analytics tools that promise more advances in technology for claims handling, underwriting and more.

There’s no limit to the number of fields an intelligent intake solution can extract from the unstructured documents typically involved in a commercial insurance claim. While your Chief Claims Officer may require only, say, 20 fields, your data analytics team could well be interested in 100. That would give them more data to use for predictive applications, loss modeling, actuarial projects and more.

Fraud detection is just one example. More than 7,000 insurance companies collect over $1 trillion in premiums each year, the FBI estimates, making them a prime target for illegal activity. The total cost of insurance fraud exceeds $40 billion per year, the FBI says – and that doesn’t include health insurance.

Fraud occurs in about 10% of property-casualty insurance losses, and fraud costs more than $300 billion per year in the U.S. alone, according to the Coalition Against Insurance Fraud. That’s why insurers are investing in technology to help them combat fraud. Nearly two-thirds of carriers are investing in predictive analytics while more than one in five are or plan to invest in AI, according to the Coalition.

Both methods can be a boon for fraud detection. AI machine learning algorithms, especially, can quickly find correlations that indicate fraud among FNOLs, police reports, and various forms that human analysts would be hard-pressed to find. And the ML tools can do it instantly.

In general, all of these tools work from data that’s in a structured format. That makes an intelligent intake platform that takes unstructured content and turns it into structured data all the more valuable.

Claims process automation is clearly the future for commercial insurance companies. To learn more, click below for an interactive demo, a free trial or to get in touch with any questions.

Share on social:

Unstructured Unlocked podcast

November 20, 2023 | E34

Unstructured Unlocked episode 34: How generative AI empowers insurers to increase efficiency without compromising security

podcast episode artwork
November 8, 2023 | E33

Unstructured Unlocked episode 33 with Terry Luciani, Nexus Vendor Ecosystem Leader at EY

podcast episode artwork
October 25, 2023 | E32

Unstructured Unlocked episode 32 with James Wright, Head of Technology at Beazley Digital

podcast episode artwork

Get started with Indico

Schedule
1-1 Demo

Join
Monthly Live Demo

Self-Guided
Interactive Demo

Resources

Blog

Gain insights from experts in automation, data, machine learning, and digital transformation.

Unstructured Unlocked

Enterprise leaders discuss how to unlock value from unstructured data.

YouTube Channel

Check out our YouTube channel to see clips from our podcast and more.