Try : Insurtech, Application Development









Dev Ops(2)

Enterprise Solution(12)




Augmented Reality(7)

Customer Journey(6)


User Experience(19)

AI in Insurance(17)


Product Innovation(26)


Artificial Intelligence(76)



Cognitive Computing(6)

Computer Vision(5)

Data Science(11)


Intelligent Automation(19)

Machine Learning(41)

Natural Language Processing(5)

How can Artificial Intelligence settle Insurance Claims in five minutes?

Originally published on

If you’ve ever been in the position of having to file an insurance claim, you would agree that it isn’t the most pleasant experience that you’ve likely ever encountered.

In fact, according to J.D. Power’s 2018 Insurance Customer Satisfaction Studymanaging time expectations is the key driver of satisfaction — meaning, a prompt claim settlement is still the best advertisable punch line for insurance firms. Time-to-settle satisfaction ratings were found to be 1.9 points lower even when the time frame was relatively short and insurers still missed customer timing expectations.

So what should an established insurance company do, to be at par with the customer’s desires of modern service standards? The question becomes even more pertinent when the insurance sector is still lagging behind consumer internet giants like Amazon, Uber who are creating newer levels of customer expectation. Lemonade, MetroMile and others are already taking significant market share away from traditional insurance carriers by facilitating experiences that were previously unheard of in the insurance trade.

Today, Lemonade contends that with AI, it has settled a claim in just 3 seconds! While a new era of claims settlement benchmarks are being set with AI, the industry is shifting their attitude towards embracing the real potential of intelligent technologies that can shave-off valuable time and money from the firm’s bottom-line.

How AI integrates across the Insurance Claims Life Cycle

For this entire process to materialize — from the customer filling out the claim information online, to receiving the amount in a bank account within a short amount of time, and have the entire process be completely automated without any interference, bias, or the whims of human prejudice.

How does this come about? How does a system understand large volumes of information that requires subjective, human-like interpretation?

The answer lies within the cognitive abilities of AI systems.

For some insurers the thought that readily comes to mind is — Surely, it must be quite difficult to achieve this in real-world scenarios. Well, the answer is — NO, it isn’t!

Indeed, there are numerous examples of real-world cases that have already been implemented or are presently in use. To understand how these systems work, we need to break down the entire process into multiple steps, and see how each step is using AI and then passing over the control to the next step for further processing.

How It Works
For the AI-enabled health insurance claims cycle, there are a few distinct steps in the entire process.

Analysis and abstraction

The following information is first extracted from medical documents (diagnosis reports, admission & discharge summaries etc.)

  1. Cause, manifestation, location, severity, encounter, and type of injury or disease — along with & related ICD Codes for injury or disease in textual format.
  2. CPT Codes — procedures or service performed on a patient, are also extracted.

There are in essence two different systems. The first one (described above) processes the information that is presented to it, while the other looks from the angle of genuineness of the information. The latter is the fraud detection system (Fraud, Abuse & Wastage Analyzer) that goes into critical examination of claim documents from the fraud, abuse and wastage perspective.

Fraud, Abuse & Wastage Analyzer

Insurance companies audit about 10% of their total claims. Out of which around 4–5% are found to be illegitimate. But the problem is that the results of these audit findings are available much after the claim has been settled, following which recovering back the money already paid for unsustainable claims is not that easy.

This means that companies are losing big sums on fraudulent claims. But is there a way by which insurers can sniff out fraud in real time while the claim is under processing?

With Cognitive AI technologies available today, this is achievable. All you need is a system that analyses hundreds and thousands of combinations of symptoms, diagnoses and comes up with possible suggested treatments. The suggestions are based on the learnings from past instances of cases that has been exposed to the AI system.

The suggested treatments’ tentative cost — based on the location, hospital, etc., is compared with the actual cost of the treatment. If the difference suggests an anomaly, then the case is flagged for review.

Automated processing of medical invoices

Now if your Fraud Analyzer finds no problem with a claim, how can you expedite its processing? Processing requires gathering information from all medical invoices, categorizing them into benefit buckets, and then finalizing the amount allowed under each head. Advanced systems can automate this entire process, ruling out manual intervention in most of these cases.

Recent AI systems have the capability of extracting line items from a scanned medical invoice image. This is achieved through a multistep process, outlined below.

  1. Localizing text on the medical invoice. This gives the bounding boxes around all texts.
  2. Running all localized boxes against a Scene Text Decoder trained using a LSTM and a Sequence Neural network.
  3. Applying Levenshtein Distance Correction for better accuracy.
  4. Mapping each line item against an insurer specific category.

Each line item is iterated over and looked up against the policy limits to get its upper limit. Each line item amount is aggregated to finally get the final settlement amount.

If the final settlement amount is within the limits set for straight through processing and no flags are raised by the Fraud, Abuse & Wastage Analyzer, then the claim is sent to billing for processing.

Moving Ahead With AI Enabled Claims
Today, AI transforms the insurance claims cycle with greater accuracy, speed and productivity, at a fraction of the cost (in the long run) — while delivering enhanced decision making capabilities and a superior experience in customer service. While, in the past, these innovations were overlooked and undervalued for the impact they produced — the insurers of today need to identify the proper use cases that match their organization’s needs and the significant value they can deliver to the customers of tomorrow. The cardinal rule is to — start small through feasible pilots, that will first bring lost dividends back into the organization.


Knowledge thats worth delivered in your inbox

Chatbots are the assistants of the future and they are taking the Internet by storm. Ever since their first appearance in 1994, the goal was to create an AI that could conduct a real dialogue with their interlocutors. The purpose is to free up customer service agents’ time so they could focus on more delicate tasks- which require a more human approach.

If you are thinking about including a chatbot on your website, here are the things you need to keep in mind to boost customer engagement and deliver high-quality services.

Define your audience

First things first- think about who will be interacting with the chatbot? Who are your customers? How do they talk? How can you address them in a way they’ll enjoy? How can you help them?

For instance, if your company sells clothes that are mostly designed for young adults, using a less formal tone will be much more appealing to them.

Lisa Wright, a customer service specialist at Trust My Paper advice: “Customer service calls are usually recorded, so listening to a few of them can be a good place to start designing your chatbot’s lines of dialogue.”

Give your bot some character

People don’t like to talk to plain, simple robots. Therefore, giving your chatbot some personality is a must. Some brands prefer naming their chatbots and even design an animated character for them. This makes the interaction more real.

For example, The SmarterChild chatbot- designed back in 2000, was able to speak to around 2,50,000 humans every day with funny, sad, and sarcastic emotions.

However, the chatbot’s character needs to match your brand identity and at the same time- appeal to customers. Think about – how would the bot speak, if they were real? Are there some phrases or words they would never use? Do they tell jokes? All these need to be well-thought through, before going into the chatbot writing and design phase.

According to a report published by Ubisend in 2017, 69% of customers use the chatbot to get an instant answer. Only 15% of them would interact for fun. Thus, don’t sacrifice the performance for personality. 

Also read – 5 Key Success Metrics for Chatbots

Revise your goals before chatbot writing

Alexa- Amazon bot has 30+ skills which include scheduling an appointment, booking a cab, reading news, playing music, controlling a smartphone, and more. However, every business bot doesn’t need to be a pro in every assisting job.

Before entering the writing phase, think over once again – WHY you need a chatbot? Will it help customer service only? Or will it also help in website navigation, purchase, return, refund, etc.?

Usually, customers want one of the three things when they visit your site: an answer to something they’re looking for, make a purchase, or a solution to their problem. You can custom build your chatbot to tackle either one or all of these three situations. Many brands use chatbots to create tailored products for their clients.  

Cover all possible scenarios

When you start writing the dialogue, consider the fact that a conversation can go in many directions. To ensure that all the situations are covered- start with a flowchart of all possible questions and the answers you chatbot can give.

To further simplify your chatbot writing, take care of one scenario at a time and focus on keeping the conversation short and simple. If the customer is too specific or is not satisfied with the bot’s response, do not hesitate to redirect them to your customer service representatives.

For instance, Xiaocle is one of the most successful interactive chatbots launched by Microsoft in July 2014. Within three months of its launch, Xiaocle accomplished over 0.5 billion conversations. In fact, speakers couldn’t understand that they’re talking to a bot for 10 minutes.

Also read – Why should businesses consider chatbots?

This article is contributed to Mantra Labs by Dorian Martin. Dorian is an established blogger and content writer for business, career, education, marketing, academics, and more.


Knowledge thats worth delivered in your inbox

The antiquated commodity of Financial ‘Coverage & Protection’ is getting a new make-over.  Conventional epigrams like ‘Insurance is sold and not bought’ are becoming passé. Customers are now more open than ever before to buying insurance as opposed to being sold by an agent.  The industry itself is witnessing an accelerated digitalization momentum on the backs of 4G, Augmented Reality, and Artificial Intelligence-based technologies like Machine Learning & NLP.

As new technologies and consumer habits keep evolving, so are insurance business models. The reality for many insurance carriers is that they still don’t understand their customers with great accuracy and detail, which is where intermediaries like agents and distributors still hold incredible market power.

On the other hand, distribution channels are turning hybrid, which is forcing carriers to be proficient in their entire channel mix. Customer expectations for 2020 will begin to reflect more simplicity and transparency in their mobility & speed of service delivery.

A recently published Gartner Hype Cycle highlights 29 new and emerging technologies that are bound for greater business impact, that will ultimately dissolve into the fabric of Insurance.

For 2020 and beyond, newer technologies are emerging along with older but more progressively maturing ones creating a wider stream of opportunities for businesses.


Irrespective of the technology application adopted by insurers — real, actionable insights is the name of the game. Without it, there can be no long term gains. Forrester research explains “Those that are truly insights-driven businesses will steal $1.2 trillion per annum from their less-informed peers by 2020”.

Based on the major trends identified in the Hype Cycle, 5 of the most near-term disruptive technologies and their use cases, are profiled below.

  1. Emotion AI
    Emotion Artificial Intelligence (AI) is purported to detect insurance fraud based on the audio analysis of the caller. This means that an AI system can decisively measure, understand, simulate and react to human emotions in a natural way.

    F0r Insurers, sentiment and tone analysis captured from chatbots fitted with emotional intelligence can reveal deeper insights into the buying propensity of an individual while also understanding the reasons influencing that decision.


Autonomous cars can also sensors, cameras or mics that relay information over the cloud that can be translated into insights concerning the emotional state of the driver, the driving experience of the other passengers, and even the safety level within the vehicle.

Gartner estimates that at least 10% of personal devices will have emotion AI capabilities, either on-device or via the cloud by 2022. Devices with emotion AI capacity is currently around 1%.

  1. Augmented Intelligence
    Augmented Intelligence is all about process intelligence. Widely touted as the ‘future of decision-making’, this technology involves a blend of data, analytics and AI working in parallel with human judgement. If Scripting is rules based automation, then ‘Augmenting’ is engagement and decision oriented.

    This manifests today for most insurance carriers as an automated back-office task, but over the next few years, this technology will be found in almost all internal and customer facing operations. Insurers can potentially offer personalised services based on the client’s individual capacity and exposure to risk — creating opportunities for cross/up-selling.

Source: Gartner Data Analytics Trends for 2019

For instance, Online Identity Verification is an example of a real-time application that not only enhances human’s decision making ability, but also requires human intervention in only highly critical cases. The Global value from Augmented AI Tools will touch $4 Trillion by 2022.

  1. AR Cloud
    The AR Cloud is simply put a real-time 3D map of an environment, overlayed onto the real World. Through this, experiences and information can be shared without being tied down to a specific location. Placing virtual content using real world coordinates with associated meta-data can be instantly shared and accessed from any device.

    For insurers, there is a wide range of opportunities to entice shopping customers on an AR-Cloud based platform by presenting personalized insurance products relevant to the items they are considering buying.

    The AR ecosystem will be a great way to explain insurance plans to customers, provide training and guidance for employees, assist in real-time damage estimation, improve the quality of ‘moment-of-truth’ engagements. This affords modern insurance products to co-exist seamlessly along the buying journey.

  2. Personification
    Personification is a technology that is wholly dependent on speech and interaction. Through this, people can anthropomorphize themselves and create avatars that can form complex relationships. The Virtual Reality-based concept will be the next way of communicating and forming new interactions.

    VR Applications such as  accident recreation, customer education and live risk assessment, can help insurers lower costs for its customers and personalise the experience.

    Brands have already begun working their way into this space, because as they see it — if younger generations are going to invariably use this technology for longer portions of their day for work, productivity, research, entertainment, even role-playing games, they will shop and buy this way too.

  3. Flying Autonomous Vehicles and Light Cargo Drones
    Although this technology is only a decade away from being commercially realized, the non-flying form is about to make its greatest impact since its original conception. Regulations are the biggest obstacle to the technology taking off, while its functionality continues to improve.

    The Transportation & Logistics ecosystem is on the brink of a complete shift, which will create a demand for a wide array of insurance related products and services that covers autonomous vehicles and cargo delivery using light drones.

While automation continues to bridge the gaps, InsurTechs and Insurance Carriers will need to embrace ahead of the curve and adopt newer strategies to drive sustainable growth.

Mantra Labs is an InsurTech100 company solving complex front & back-office processes for the Digital Insurer. To know more about our products & solutions, drop us a line at


Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top

May i help you?

Our Website is
Best Experienced on
Chrome & Safari

safari icon