Applying Predictive Analytics for Insurance Assumptions—Setting Practical Lessons

Graphic:

Excerpt:

3. Identify pockets of good and poor model performance. Even if you can’t fix it, you can use this info in future UW decisions. I really like one- and two-dimensional views (e.g., age x pension amount) and performance across 50 or 100 largest plans—this is the precision level at which plans are actually quoted. (See Figure 3.)

What size of unexplained A/E residual is satisfactory at pricing segment level? How often will it occur in your future pricing universe? For example, 1-2% residual is probably OK. Ten to 20% in a popular segment likely indicates you have a model specification issue to explore.

Positive residuals mean that actual mortality data is higher than the model predicts (A>E). If the model is used for pricing this case, longevity pricing will be lower than if you had just followed the data, leading to a possible risk of not being competitive. Negative residuals mean A<E, predicted mortality being too high versus historical data, and a possible risk of price being too low.

Author(s): Lenny Shteyman, MAAA, FSA, CFA

Publication Date: September/October 2021

Publication Site: Contingencies

Insuring Another Disaster

Excerpt:

Leave it to California lawmakers, however, to cast aside thousands of years of complex commercial history in a misguided attempt to fix an admittedly legitimate insurance problem. Thanks to Proposition 103, a 1988 ballot measure, California already has a distorted insurance market that gives the insurance commissioner czar-like powers to approve rate increases and impose rate decreases.

Because of that law, insurers have a tough time adjusting rates to manage their risks. It’s a long, cumbersome, and antagonistic government process to adjust rates. Their other lever for ensuring solvency is to reduce their underwriting risks by, say, not writing fire-insurance policies to homeowners who live in high fire-risk areas or car insurance policies to drivers with multiple DUIs.

….

Instead, California Assemblymember Marc Levine, D-Marin County, has introduced Assembly Bill 1522, which would prohibit insurers from canceling insurance policies solely because a home or business is located in a high-risk wildfire area. It epitomizes California’s economically illiterate edict approach.

Author(s): Steven Greenhut

Publication Date: 29 April 2021

Publication Site: The American Spectator

Bricks Without Straw?

Link: https://www.rstreet.org/2021/03/30/bricks-without-straw/

Excerpt:

Credit analytics firm FICO posits that the reason for the correlation of credit history and claim probability is that “individuals who closely and cautiously monitor and manage their finances tend to also take better care of their cars and homes and are, generally, more diligent in their risk management habits.” Because such individuals are found across demographic classifications, the discrimination argument becomes hard to uphold.

If insurers find that credit scores have bearing on accident propensity, insurers should be allowed to use them. Preventing insurers from deploying basic tools required to generate appropriate risk-adjusted prices leads to mispricing of risk, harming insurance buyers as well as insurers. What is more, such deprivation leads to unintended negative consequences—an unfair socialization of risk, leaving customers either overcharged or undercharged. Executive fiat prohibiting insurers from accessing the tools of their trade is tantamount to Pharaoh ordering the Israelites of old to make bricks without straw. Bad business, bad policy.

Author(s): Jerry Theodorou

Publication Date: 30 March 2021

Publication Site: R Street

Senators quiz insurers on climate-related underwriting

Link: https://www.businessinsurance.com/article/20210326/NEWS06/912340735/Senators-quiz-insurers-on-climate-related-underwriting

Additional link: https://static1.squarespace.com/static/5b7c9307f79392b49031d551/t/605cf32f9d526442eb0bca0c/1616704303928/Senators%27+Letter+-+Chubb.pdf

Excerpt:

Democratic lawmakers have called on U.S. insurers including American International Group Inc., Berkshire Hathaway, Chubb Ltd., Liberty Mutual Insurance Co., MetLife Inc. and Travelers Cos. Inc. to explain how their fossil fuel underwriting policies align with their commitments to sustainability.

In a letter dated March 24, Sen. Sheldon Whitehouse, D-Rhode Island, and Senators Jeffrey A. Merkley, D-Oregon, Elizabeth Warren, D-Massachusetts, and Chris Van Hollen, D-Maryland, request information on each insurer’s fossil fuel underwriting and investment policies.

“An increasing number of your competitors have stopped underwriting coal and other fossil fuel projects and/or restricted their investments in coal and certain dirty and environmentally damaging oil and gas projects such as tar sands,” the letter said.

Excerpt:

Author(s): Claire Wilkinson

Publication Date: 26 March 2021

Publication Site: Business Insurance

A Primer on Insurance Policies and Genetics

Link: https://www.soa.org/resources/research-reports/2021/primer-ins-policies-genetics/

Full report: https://www.soa.org/globalassets/assets/files/resources/research-report/2021/primer-ins-policies-genetics-report.pdf

Graphic:

Excerpt:

A new subset of Somatic non-blueprint information is the growing field of Epigenetics, defined as changes ‘above
the genetics,’ where it has recently been found that lifestyle choices also induce non-heritable physical or chemical
changes directly on a person’s DNA after birth, and can be measured by isolating the DNA and revealing these
features. The U.S. Center for Disease Control states: “Epigenetics is the study of how your behaviors and
environment can cause changes that affect the way your genes work. Unlike genetic changes, epigenetic changes
are reversible and do not change your DNA sequence.” (9)


An example of the latter is a finding that the tips of our chromosomes – called telomeres – can shorten or lengthen
in correlation with health status and ‘biological aging,’ a finding that was the subject of a 2009 Nobel Prize (10). An
additional example of epigenetics is in tobacco use, shown below, and generally discussed at the 2020 SOA Health
Conference by Dr. Brian Chen at this link https://webcasts.soa.org/products/actuarial-innovation-and-technologyupdate-on-recent-research#tab-product_tab_speaker_s.

Author(s): James Timmins

Publication Date: March 2021

Publication Site: Society of Actuaries

Ethics and use of Data Sources for Underwriting ft. Neil Raden and Kevin Pledge -NSNA(Ep.4)

Video:

Description:

The video features Neil Raden who is the author of ethical use of AI for Actuaries. Alongside him , it features Kevin Pledge who is CEO of Acceptiv , FSA,FIA and chair of Innovation and Research Committee of SOA. We discuss about the issue of ethics and about the use of new data sources in the recent Emerging issues in Underwriting Survey Report by IfOA.

Authors: Harsh Jaitak, Kevin Pledge, Neil Raden

Publication Date: 17 March 2021

Publication Site: TBD Actuarial at YouTube