5 insurance use cases for machine learning

Link: https://www.dig-in.com/opinion/5-use-cases-for-machine-learning-in-the-insurance-industry

Excerpt:

4. Fraud detection

Unfortunately, fraud is rampant in the insurance industry. Property and casualty insurance alone loses about $30 billion to fraud every year, and fraud occurs in nearly 10% of all P&C losses. ML can mitigate this issue by identifying potential claim situations early in the process. Flagging early allows insurers to investigate and correctly identify a fraudulent claim. 

5. Claims processing

Claims processing is notoriously arduous and time-consuming. ML technology is a tool to reduce processing costs and time, from the initial claim submission to reviewing coverages. Moreover, ML supports a great customer experience because it allows the insured to check the status of their claim without having to reach out to their broker/adjuster.

Author(s): Lisa Rosenblate

Publication Date: 9 Sept 2022

Publication Site: Digital Insurance

Social and Other Determinants of Life Insurance Demand

Link: https://www.soa.org/resources/research-reports/2022/determinants-life-insurance/

Report: https://www.soa.org/4a50aa/globalassets/assets/files/resources/research-report/2022/determinants-life-insurance.pdf

Graphic:

Excerpt:

The authors examine 19 factors to determine which were most closely linked to permanent and term life insurance premiums sold in the United States in 2020. With spatial regression analysis using multi-scale geographically weighted regression (MGWR) approach, the authors find the following 5 covariates to be the most statistically significant for and positively correlated with permanent insurance sold: household income, percentage of the population that is African American, education, health insurance, and Gini index (a statistical measure of wealth inequality). For term insurance sold, the 5 most significant covariates are household income, education, Gini index, percentage of households with no vehicles, and health insurance. Their relationships with term insurance sold are positive except for the percentage of households with no vehicles.

Author(s):

Wilmer Martinez
Kyran Cupido
Petar Jevtic
Jianxi Su

Publication Date: August 2022

Publication Site: SOA

Current Issues in Insurance

Link: https://www.banking.senate.gov/hearings/current-issues-in-insurance

Excerpt: https://www.banking.senate.gov/imo/media/doc/Brown%20Statement%209-8-22.pdf

Statement from Chair Sherrod Brown (D-OH)

Every American needs insurance – whether it’s auto insurance to protect us when we’re on the
road, or homeowners’ insurance to protect the biggest investment for most families, or life
insurance to cement your family’s financial security in the event of a tragedy.
It’s our job to make sure that the industry is protecting Americans’ hard-earned money – not
putting it at risk.
American insurance companies are regulated by state insurance commissioners. The state-based
system of insurance regulation is historic, and ensures local markets and needs are taken into
consideration.
The National Association of Insurance Commissioners coordinates state commissioners across
all jurisdictions, to identify and address risks to the entire system.
In the Wall Street Reform Act, Congress created the Federal Insurance Office within the
Treasury Department to promote national coordination in the insurance sector. It’s common
sense – insurers operate across all state jurisdictions and internationally.
I’m pleased to have both the Maryland Commissioner Kathleen Birrane on behalf of the NAIC,
and Director Seitz of FIO testify today.
If we’re going to keep Americans’ hard-earned money safe, it is more important than ever that
they work together.
Today we’ll explore many important topics.
For example, three months ago, Lockheed Martin transferred $4.3 billion of its pensions to
Athene Holding – an insurance holding company specializing in life insurance and owned by the
private equity firm, Apollo Global Management.
Overnight, Lockheed Martin employees and retirees were notified that their pensions would be
managed by Athene and no longer governed by ERISA or the Pension Benefit Guaranty
Corporation.
This is just one recent example of private equity giants’ expansion into people’s pensions and the
insurance industry.
We know that workers end up worse off when Wall Street private equity firms get involved.
We’ve seen it over and over, in industry after industry.
In March, I asked the NAIC and FIO to look into private equity’s expansion into similar pensionrisk transfer transactions. We need to understand the risks to workers whose financial security
depends on pension and retirement programs.
The NAIC and FIO provided thoughtful responses to my letter. The NAIC has been monitoring
the risk-taking behavior of private equity-owned insurers.
FIO has done similar work, and also looked at the wider interconnectedness of insurance and
reinsurance markets across the world. Those connections have added to systemic risk concerns,
because U.S. insurance companies depend even more on the financial health of insurance
companies outside the U.S.
Taken together, our insurance authorities are focused on these emerging and complex risks to
safeguard our economy.
Our communities and families rely on insurance companies to protect their loved ones, their
homes, small business, and so many parts of our lives. We can’t ignore when risks build up, or
firms behave irresponsibly.
And we know who always pays the price when they do. It’s not insurance executives. It’s not
private equity executives. It’s not Wall Street.
It’s workers and their families. And it’s taxpayers, who were forced to bail out AIG 15 years ago.
That should never happen again.
That also means looking around the corner to make sure the industry and agencies are prepared
for risks as they develop. As more Americans face increasingly severe climate catastrophes like
wildfires and hurricanes each year, we need to help communities prepare – and we need to
ensure insurance watchdogs and the companies they oversee are prepared.
In the aftermath of some of these natural disasters, we have seen instances where insurers either
raise prices or stop offering insurance altogether, leaving families and businesses struggling to
find affordable coverage as they rebuild their lives and communities.
We also know this industry has a long history of racial discrimination, just like so many big
industries.
Black and brown families face more difficulty in getting insurance across the board. We’ve seen
this happen in auto insurance.
Earlier this year, The New York Times also reported that customers, insurance agents, and
employees sued State Farm for discrimination in the workplace and in paying out claims.
My colleague Chairwoman Waters has been working on learning more about this as well. Her
committee recently requested information about large life and P&C insurers’ involvement in
financing chattel slavery.
And I’m glad FIO and NAIC are also working on this. NAIC is investigating through its Special
Committee on Race and Insurance.
And I look forward to reviewing FIO’s upcoming report on availability and affordability of auto
insurance, and hope it will shed more light on racial equity in accessing this insurance.
Finally, later this year, the International Association of Insurance Supervisors will meet to
consider whether the U.S. insurance system’s review of capital adequacy standards meets
international criteria.
Because we regulate insurance differently here in the U.S., where state and local markets and
international markets are served by the same companies, it’s important that representatives of the
U.S. system like FIO and the NAIC advocate for fair treatment by the international regulators.
And now that the Fed Vice Chair for Supervision has been confirmed, Michael Barr and the
offices testifying here today will get to work with our international counterparts in this process.
All of these issues show how critical the work of FIO and NAIC is to our economy’s health and
stability. I expect FIO and NAIC to prioritize monitoring these risks in their ongoing work.

Publication Date: 8 Sept 2022

Publication Site: COMMITTEE ON BANKING, HOUSING, AND URBAN AFFAIRS of the U.S. Senate

Private Equity (PE)-Owned U.S. Insurers’ Investments Decrease as of Year-End
2021; Number of PE-Owned U.S. Insurers Increases

Link: https://content.naic.org/sites/default/files/capital-markets-special-reports-PE-owned-YE2021.pdf

Graphic:

Excerpt:

The BACV of total cash and invested assets for PE-owned insurers was about 6% of the U.S. insurance
industry’s $8.0 trillion at year-end 2021, down slightly from 6.5% of total cash and invested assets at
year-end 2020. The number of PE-owned insurers, however, increased to 132 in 2021 from 117 in 2020,
but they were about 3% of the total number of legal entity insurers at both year-end 2021 and year-end 2020.

Consistent with prior years, U.S. insurers have been identified as PE-owned via a manual process.
That is, the NAIC Capital Markets Bureau identifies PE-owned insurers to be those who reported any
percentage of ownership by a PE firm in Schedule Y, and other means of identification such as using
third-party sources, including directly from state regulators. As such, the number of U.S. insurers that
are PE-owned continues to evolve.1
Life companies continue to account for a significant proportion of PE-owned insurer investments at
year-end 2021, at 95% of total cash and invested assets (see Table 1). This represents a small decrease
from 97% at year-end 2020 (see Table 2). Notwithstanding, there was a slight increase in PE-owned
insurer investments for property/casualty (P/C) companies, to 4% at year-end 2021, compared to 3% the
prior year. In addition, there was also a small increase in total BACV for PE-owned title and health
companies’ investments, at about $1.1 billion at year-end 2021, compared to under $1 billion at yearend 2020.

Author(s): Jennifer Johnson and Jean-Baptiste Carelus

Publication Date: 19 Sept 2022

Publication Site: NAIC Special Capital Markets Reports

Insurers Must Reach Millennials and Gen Zers. Here’s How

Link: https://www.thinkadvisor.com/2022/09/12/insurers-must-reach-millennials-and-gen-zers-heres-how/

Excerpt:

Based on the widely used Pew Research definitions, the millennials are turning 26 through 41 this year, and Gen Zers are turning 10 through 25.

More than half of Gen Zers ages 16 through 24 are already in the workforce.

It’s time for carriers to innovate rapidly to respond to the buying preferences of members of these generations.

…..

As an example, if the target customers are millennials and Gen Zers who need a simple term life insurance solution, you may want to focus on instant decision underwriting and lower face amounts to meet the most basic needs.

This approach could mean that many historical riders and features are actually not necessary.

It likely also means that the tools used in underwriting need to focus on information that is available instantly as opposed to traditional methods that could take weeks or even months.

Author(s): Jeremy Bill

Publication Date: 12 Sept 2022

Publication Site: Think Advisor

Group Term Life – Results of 2021 U.S. Market Survey

Link: https://www.genre.com/knowledge/publications/2022/june/surveylhgtlsum2206-en

Graphic:

Excerpt:

Gen Re is pleased to share the results from our latest U.S. Group Term Life Market Survey, an industry benchmarking survey covering the Group Term Life (GTL) and AD&D industry. The survey tracks sales and in‑force results as well as lapse rate and employee-paid data.

Twenty-one of the 29 companies participating in the 2021 survey have provided Group Term Life data over the past 10 survey years.

Twenty-nine companies provided GTL results for 2021. Twenty-seven provided AD&D results. On a combined basis, total GTL and AD&D in‑force premium reached $31.6 billion, with GTL representing the majority (94%) of the total. (Exhibit A)

For GTL in‑force premium, reported industry growth has ranged between 2% and 5% over the past 10 years. In 2021, in‑force premium grew by 6% compared to 2020.

After a five-year low of 1% growth in 2020, AD&D in‑force premium rose by 3% in 2021. (Exhibit B)

Author(s): Nicole Conti

Publication Date: 7 June 2022

Publication Site: Gen Re

Individual Disability Carriers Steer Through Uncertain Times

Link: https://www.genre.com/knowledge/blog/2022/august/individual-disability-carriers-steer-through-uncertain-times-en

Graphic:

Excerpt:

Seventeen carriers participated in our 2021 U.S. Individual Disability Market Survey, representing 99% of the market and $5.1 billion of in‑force premium. New sales in 2021 were $399 million which was flat when compared to new sales in 2020. Breaking this down even further, both Non-Cancelable (Non‑Can) and Guaranteed Renewable (GR) sales were flat when compared to 2020. Non‑Can was down 0.1% and GR was up 0.5%. Of the $399 million in total new sales premium, Non‑Can products represent 84% or $334 million, and GR is 16% or $65 million.

When asked about meeting their 2021 sales goals, 47% of the responding companies said they missed theirs. 18% of the companies met and 35% of the companies exceeded their goals. Some of the reasons given for missing sales goals were:

COVID limited face-to-face contact with consumers

Agents were focused on other products such as life insurance

The number of new policies issued grew by 2% to over 251,000 and total benefit amounts increased by 3% to more than $1.6 billion. The medical market continues to be a main driver of new business. In 2021, close to 30% of all new policies sold were in the medical market; however, the industry did see some growth down-market with increases in the number of new policies sold in the blue collar space.

Author(s): Steve Woods

Publication Date: 3 Aug 2022

Publication Site: Gen Re Perspective

Coordinating VM-31 With ASOP No. 56 Modeling

Link: https://www.soa.org/sections/financial-reporting/financial-reporting-newsletter/2022/july/fr-2022-07-rudolph/

Excerpt:

In the PBRAR, VM-31 3.D.2.e.(iv) requires the actuary to discuss “which risks, if any, are not included in the model” and 3.D.2.e.(v) requires a discussion of “any limitations of the model that could materially impact the NPR [net premium reserve], DR [deterministic reserve] or SR [stochastic reserve].” ASOP No. 56 Section 3.2 states that, when expressing an opinion on or communicating results of the model, the actuary should understand: (a) important aspects of the model being used, including its basic operations, dependencies, and sensitivities; (b) known weaknesses in assumptions used as input and known weaknesses in methods or other known limitations of the model that have material implications; and (c) limitations of data or information, time constraints, or other practical considerations that could materially impact the model’s ability to meet its intended purpose.

Together, both VM-31 and ASOP No. 56 require the actuary (i.e., any actuary working with or responsible for the model and its output) to not only know and understand but communicate these limitations to stakeholders. An example of this may be reinsurance modeling. A common technique in modeling the many treaties of yearly renewable term (YRT) reinsurance of a given cohort of policies is to use a simplification, where YRT premium rates are blended according to a weighted average of net amounts at risk. That is to say, the treaties are not modeled seriatim but as an aggregate or blended treaty applicable to amounts in excess of retention. This approach assumes each third-party reinsurer is as solvent as the next. The actuary must ask, “Is there a risk that is ignored by the model because of the approach to modeling YRT reinsurance?” and “Does this simplification present a limitation that could materially impact the net premium reserve, deterministic reserve or stochastic reserve?”

Understanding limitations of a model requires understanding the end-to-end process that moves from data and assumptions to results and analysis. The extract-transform-load (ETL) process actually fits well with the ASOP No. 56 definition of a model, which is: “A model consists of three components: an information input component, which delivers data and assumptions to the model; a processing component, which transforms input into output; and a results component, which translates the output into useful business information.” Many actuaries work with models on a daily basis, yet it helps to revisit this important definition. Many would not recognize the routine step of accessing the policy level data necessary to create an in-force file as part of the model itself. The actuary should ask, “Are there risks introduced by the frontend or backend processing in the ETL routine?” and “What mitigations has the company established over time to address these risks?”

Author(s): Karen K. Rudolph

Publication Date: July 2022

Publication Site: SOA Financial Reporter

Insurance Industry Outlook

Link: https://www.selbyjennings.com/blog/2022/02/insurance-industry-outlook

Excerpt:

In health insurance, with the continual spike in Medicare, we forecast a huge shift towards this area and Medicaid in 2022, and beyond. With the way that the market has evolved, it’s possible that actuaries with experience in Medicare will be in-demand, especially as bid season is fast approaching. Alongside proficiency in risk adjustment, the Society of Actuaries (SOA) recently added a new exam for predictive analytics.

As always, for the property & casualty sector, the key modelling skillsets going into 2022 is R and Python. With the rise in cyber and ransomware attacks, this might result in a boom in cyber insurance and simultaneously the specialists, minimum of 2-3 years in underwriting, to better service this demand. In addition to fluency in modelling, designations from Associates of the Casualty Actuary Society (ACAS) and Fellowship of the Casualty Actuary Society (FCAS), has importance to employers and therefore significant currency in the market.

Publication Date: July 2022

Publication Site: Selby Jennings

Covid-19 Impact on the South African Life Insurance Industry: What Can we Learn?

Link: https://www.soa.org/sections/international/international-newsletter/2022/july/isn-2022-07-hoberg/

Graphic:

Excerpt:

The impact of Covid-19 in South Africa in terms of excess deaths was substantial, when considering the reported excess deaths as published by the South African Medical Research Council (SAMRC).[4] Please note that in this article we will not further consider whether all excess deaths can be directly attributed to Covid-19, however, as per the article “Correlation of Excess Natural Deaths with Other Measures of the Covid-19 Pandemic in South Africa,”[5] it is estimated that 85 percent to 95 percent of excess natural deaths are attributable to Covid-19.

Based on the SAMRC excess deaths, taking the expected plus excess deaths as Actual and expected natural deaths as per their methodology as Expected, we observe an Actual versus Expected (AvE) ratio of 116 percent in 2020, a ratio of 131 percent in 2021, and a ratio of 113 percent in 2022 up to May 1. When we look at the AvE for each wave, we can see that the 2nd wave (predominantly Beta variant) and the 3rd wave (predominantly Delta variant), had the most severe impact on the general population (see figure 2 and figure 3)

Author(s): Idelia Hoberg

Publication Date: July 2022

Publication Site: SOA International News

Event: The Private Market for Flood Insurance

Link: https://www.rstreet.org/2022/07/20/event-the-private-market-for-flood-insurance/

Video:

Excerpt:

The private market for flood insurance in the United States measures approximately $300 million in annual premium. This is less than 10 percent of the $3.7 billion in flood insurance premium written by the federal government’s National Flood Insurance Program (NFIP). Private insurers offering flood insurance are not operating on the same playing field because many NFIP policies are subsidized and underpriced. The creativity of private insurers, guided by the dynamics of a free and competitive market, will eventually drive out inefficiency and false price signals, and make available to homeowners and businesses the flood insurance they need at the right cost.

We invite you to an online discussion examining the obstacles and opportunities for private insurers featuring flood insurance entrepreneur Trevor Burgess, and R Street’s Jerry Theodorou and Caroline Melear.

Author(s): Jerry Theodorou, Trevor Burgess, Caroline Melear

Publication Date: 20 Jul 2022

Publication Site: R Street

How AI can revolutionize small commercial underwriting

Link: https://www.dig-in.com/opinion/how-ai-can-revolutionize-small-commercial-underwriting

Excerpt:

Today, small commercial insurers can leverage AI/ML data and analytics as part of a holistic solution to transition from manual underwriting workflows that lean on lengthy applications and web research to one where quotes are issued and most policies are bound automatically and (nearly) instantly.

The journey has three broad phases.

Step 1: Prefill: Leveraging an array of data sources, including unstructured data sourced from computer vision algorithms, insurers can prefill application data on small commercial risks using just a business name and address. Human underwriters can then review this information against underwriting guidelines without having to chase down data through web searches or phone calls. 

Step 2: Selective automation: Based on risk appetite, certain industry classes can be identified for automated underwriting. In this environment, application data is prefilled and then automatically analyzed against insurer underwriting guidelines to determine acceptance or whether additional information is required. 

Step 3: Full-blown automation: As insurers learn from step two, it’s a short leap to step three, which is to fold additional businesses into the automated workflow. Even in a fully automated environment, there are some risk exposures that may trigger manual reviews of submissions. But by leveraging the efficiency gains delivered by application prefill and the automated underwriting of select industry classes, insurers can set themselves up to drive automation across a much wider array of risks than they ever thought possible.

Author(s): Tracey Waller

Publication Date: 29 Jun 2022

Publication Site: Digital Insurance