AIMultiple ResearchAIMultiple Research

Top 7 Technologies that Improve Insurance Underwriting in 2024

Updated on Jan 13
6 min read
Written by
Cem Dilmegani
Cem Dilmegani
Cem Dilmegani

Cem is the principal analyst at AIMultiple since 2017. AIMultiple informs hundreds of thousands of businesses (as per Similarweb) including 60% of Fortune 500 every month.

Cem's work focuses on how enterprises can leverage new technologies in AI, automation, cybersecurity(including network security, application security), data collection including web data collection and process intelligence.

View Full Profile
Top 7 Technologies that Improve Insurance Underwriting in 2024Top 7 Technologies that Improve Insurance Underwriting in 2024

AIMultiple team adheres to the ethical standards summarized in our research commitments.

Insurance industry that operated with low profit margins, is facing increased competition both in terms of price and time to serve. Insurtechs use emerging tech (e.g. advanced analytics, NLP, digital twins etc.) to serve customers faster and at lower cost. This approach resonates with customers as 85% of customers want to buy insurance policies more quickly. How can insurers keep up?

To keep up, Insurers are renewing their underwriting departments to price risk better and in less time. We explain why insurers must renew their underwriting approach and introduce seven key technologies that enable more effective underwriting.

What is effective underwriting?

Effective underwriting systems:

  • Underwrite risk at prices that optimize profits.
  • Make suitable diversification.
  • Operate at speeds acceptable to customers.

In underwriting, insurers calculate the likelihood of a loss that can affect properties, vehicles, businesses, or people. Then, insurers sell an insurance policy (i.e. an indemnity guarantee) for losses that meet certain predetermined criteria. In other words, policyholders reduce their risks by paying a certain amount. The underwriting process attempts to determine this amount as accurately as possible to maximize profit.

However, effective underwriting is not just risk assessment. The other two important components are the time required to price the risk and a portfolio strategy.

Portfolio strategy refers to diversification of liabilities and ensures longevity of insurance companies. Consider an insurance company that only insures homes in the California region. An earthquake in California could spell doom for this company. A diversification strategy helps insurance companies manage their risks more professionally.

Why is effective underwriting important now?

Because most insurers have limited profitability and improving underwriting is one of the most important levers in improving profitability.

The return on surplus (ROS) is an important ratio that provides information on how healthy the financial position of an insurance company is. To calculate it, an insurance company’s net income is divided by the assets owned by policyholders minus the company’s liabilities. The higher the result, the better the financial position.

As Figure 1 shows, the average ROS for insurance companies from 2007 to 2017 was 11.6%. However, 80 % of insurance companies had a ROS of 11.3 % or below, indicating that the median ROS is well below 11.6 % and only a very small proportion of insurance companies earn a significant amount of money. 

The same McKinsey study shows that top 20% quintile companies are those that were better prepared for the digitization process by adopting at least some of the technologies we will mention soon to facilitate their underwriting capabilities.

Figure 1: The financial performance of insurance companies varies widely.

Only top quintile insurance companies make great profits.
Source: McKinsey

1. Advanced Analytics on structured data

Advanced analytics techniques allow fast, accurate pricing while let insurers to find an optimal portfolio strategy. 

The best way of pricing risk is interpreting data regarding candidate policyholder’s background. For instance, to determine the premium of an health insurance, insurers can benefit from statistics like:

  • Age of applicant
  • Cigarette consumption
  • Alcohol consumption
  • Diet routine
  • Bad fat ratio
  • Medical check report (sugar, blood pressure etc.)
  • Exercise routine
  • Danger of his/her working environment
  • Medical recordings of applicant (any chronic illness does he/she have)
  • Medical recordings of applicant’s family

Each variable has a specific relationship to the probability of cost to the insurance company. To accurately calculate each coefficient in a short period of time, insurers use AI/ML models. These models feature high computational power and are good at predicting loss by analyzing historical data.  

Advanced analytics also helps insurers to execute portfolio strategies. An effective portfolio strategy is based on mean-variance analysis, and investors use advanced analytics models to optimize their portfolio strategies with robo-advisors for a while. Insurers have adopted similar technologies for their own diversification strategies.

Behavioral analytics can also be helpful for insurance companies to conduct effective underwriting. Such models review customers’ browsing history, clicks, location, etc., and determine their risk of committing fraud in the future. This way, insurers do not have to charge all customers for fraud and can reward their trusted policyholders.

For more, feel free to check our article on AI in underwriting.

2. Natural Language Processing (NLP)

NLP has similar benefits to advanced analytics but while using NLP, insurers leverage text and audio data for improved pricing. 

NLP is an AI/ML approach that derives meaning from text and audio. In the insurance industry, many charts and texts need to be evaluated. For example, when we follow up on a health insurance case, the client responds to questionnaires and doctors’ reports; all of these contain textual data. NLP models can extract data from these documents, categorize them and find certain correlations between certain claims and risk elements.

3. Optical Character Recognition (OCR) / Handwritten Character Recognition (HCR) 

HCR/OCR allows insurers to access unstructured text documents to automate mundane data collection tasks and extract more data for advanced analytics and NLP.

Documents are one of the means for communication between companies and individuals. Insurers need to process documents to understand their potential customers better. Two technologies support this:

  • Optical character recognition (OCR) specializes in deriving meaning from printed texts.
  • Handwritten Character Recognition (HCR) helps insurers derive meaning from handwritten documents that are still in use.

OCR and HCR can help insurers automate data entry. According to Accenture, underwriters deal with repetitive tasks like data entry more than 50% of the time. So automating such tasks can help insurers use their employees more effectively.

You can read our insurance underwriting automation article if you need more information on underwriting automation.

If you need more information on AI underwriting, see our article on AI in underwriting.

4. Digital Twins

Digital twins are computer-generated replicas of any natural object, such as humans, buildings, or automobiles that help running simulations. 

Simulations are beneficial for insurers for two reasons:

  • They can assess whether or not their portfolio strategies (diversification) are ensuring their longevity. If they do not, companies can renew their diversification strategies by targeting new locations, insured groups, insurance objects, or diversify portfolio with reinsurance strategy.
  • As mentioned above, insurers use historical data. However, for certain cases, there is a lack of historical data. For example, Mount Vesuvius in Italy has not erupted on a major scale since 1944. However, this volcano is known for destroying the Ancient Roman city of Pompeii. Insurers may want to predict the cost of such unlikely but absolutely catastrophic events. Another example is the magnitude 7 or greater earthquakes that strike California about once a decade. By predicting the cost of such catastrophic events insurers can set premium prices that ensure their long term profit.

5. Internet of things (IoT)

IoT increases the amount of data available to insurers. 

The analytics technologies were related to increasing computing power available to insurers. However, computing power without data is meaningless. IoT is the universe of smart devices that simultaneously share data about the environment in which they are deployed. Thus, IoT expands the data that AI/ML models can interpret and helps insurers make more accurate risk scoring.

It is important to examine which variables insurers have added to their menu in addition to the traditional variables they have reviewed. In Table 1, we compared the variables examined for health, property and business insurance in pre-IoT and post-IoT periods. 

Table 1: Comparison of pre-IoT/post-IoT period variables.

Pre-IoT variablesPost-IoT variables added on Pre_IoT variables
Health Insurance

1) Age of Insured
2) Answers to the questionnaire
3) Doctor report

1) Daily exercise data
2) Sleep quality data
3) Heartbeat data

Automobile Insurance

1) Segment of car
2) Previous accidents/ Police reports
3) Driver's age

1) Number of full breakes per mile
2) Miles Driven
3) Location of driving and average speed

Commercial Property Insurance1) Answers to the questionnaire
2) Industry
1) Heat of equipments used
2) Frequency of equipments used

Smartwatches-smartphones, smart cars, and smart factories-will be the primary data sources for health insurance, auto insurance, and commercial insurance, respectively.

IoT can encourage individuals to act more responsibly. Tracking individuals can be a tool to improve their behavior. For example, a driver who drives his car less often pays less for his car insurance. With pay-as-you-drive insurance, the price is based on the policyholder’s driving habits. Similarly, health insurance companies have already started rewarding policyholders who take care of their health. 

It is important to note that the rapid proliferation of smart devices increases the risk of cyberattacks. Therefore, cybersecurity insurance could be the most important insurance practice of the future.

6. Application Programming Interfaces (APIs)  

IoT is expanding database and data variability for insurers. AI/ML models provide the computing power needed to interpret data. APIs are software intermediaries that ensure the transfer of external data to insurance tools for underwriting. 

Insurers using their own hardware or adopting cloud computing to perform technology-driven underwriting. APIs help insurers extract data from external databases according to their needs. By using APIs, insurers use data storage and transfer more efficiently. Data can be stored in remote areas and APIs can fetch them. For cloud users, APIs help optimize cloud costs and increase overall business efficiency.  

If you want to understand more about how APIs can be used in the insurance industry, read Top 6 API Use Cases in the Insurance Industry.

7. Blockchain

Some data that may be useful to insurers in assessing risk may be personal data so, due to regulations like GDPR it might be hard to share such data with third parties. Also, customers may not want to share such information with third parties or are afraid that insurance companies might sell it to outsiders. Such a case is particularly relevant for health insurers, where patient data is confidential.

Because the blockchain is capable of cryptographically storing data securely, insurers can extract patient data from doctors and turn it into smart contracts without knowing who the customer really is. Policyholders can benefit from health insurance if the conditions of the predetermined smart policy are met.

To learn more you can read our blockchain insurance article.

You can check our list of top underwriting software platforms to improve your underwriting capabilities.

Also, you might want to look at our top insurance suites list.

If you are looking for an insurtech that supports your underwriting transformation we can help. 

Find the Right Vendors
Cem Dilmegani
Principal Analyst

Cem is the principal analyst at AIMultiple since 2017. AIMultiple informs hundreds of thousands of businesses (as per Similarweb) including 60% of Fortune 500 every month.

Cem's work focuses on how enterprises can leverage new technologies in AI, automation, cybersecurity(including network security, application security), data collection including web data collection and process intelligence.

Cem's work has been cited by leading global publications including Business Insider, Forbes, Washington Post, global firms like Deloitte, HPE, NGOs like World Economic Forum and supranational organizations like European Commission. You can see more reputable companies and media that referenced AIMultiple.

Cem's hands-on enterprise software experience contributes to the insights that he generates. He oversees AIMultiple benchmarks in dynamic application security testing (DAST), data loss prevention (DLP), email marketing and web data collection. Other AIMultiple industry analysts and tech team support Cem in designing, running and evaluating benchmarks.

Throughout his career, Cem served as a tech consultant, tech buyer and tech entrepreneur. He advised enterprises on their technology decisions at McKinsey & Company and Altman Solon for more than a decade. He also published a McKinsey report on digitalization.

He led technology strategy and procurement of a telco while reporting to the CEO. He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem's work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider.

Cem regularly speaks at international technology conferences. He graduated from Bogazici University as a computer engineer and holds an MBA from Columbia Business School.

Sources:

AIMultiple.com Traffic Analytics, Ranking & Audience, Similarweb.
Why Microsoft, IBM, and Google Are Ramping up Efforts on AI Ethics, Business Insider.
Microsoft invests $1 billion in OpenAI to pursue artificial intelligence that’s smarter than we are, Washington Post.
Data management barriers to AI success, Deloitte.
Empowering AI Leadership: AI C-Suite Toolkit, World Economic Forum.
Science, Research and Innovation Performance of the EU, European Commission.
Public-sector digitization: The trillion-dollar challenge, McKinsey & Company.
Hypatos gets $11.8M for a deep learning approach to document processing, TechCrunch.
We got an exclusive look at the pitch deck AI startup Hypatos used to raise $11 million, Business Insider.

To stay up-to-date on B2B tech & accelerate your enterprise:

Follow on

Next to Read

Comments

Your email address will not be published. All fields are required.

0 Comments