Predictive modeling can forecast workers’ comp claims and increase efficiency

Identifying workers’ compensation claims with potentially high costs – before those costs have developed – has, for the most part, eluded insurance and self-insured companies, even though they pay more than $60 billion in workers’ compensation benefits every year. Over 80% of all workers’ compensation costs come from a small number of unpredictable, high-cost claims. Conversely, lower-cost med-only claims account for 75% of total claims but only 5% of the cost.

These hard facts are the claims reality that insurers and self-insurers like the Intergovernmental Risk Management Agency (IRMA) face daily. Focused on improving performance and reducing costs for its 70-plus member organizations, the Chicago-area member-owned public risk pool had been looking for a way to increase efficiency regarding workers’ compensation losses while improving accident prevention and claims responses for its members’ workforce.

A major challenge to peeling back the mystery in its “unknown high-cost claims” was finding a way to access the predictive data in adjusters’ notes, case manager notes, and other sources of text data. This unstructured, free-form data could provide an early warning of potentially costly claims, but requires claims managers to read through reams of adjusters’ notes. This manual process typically delays identification of potentially problematic claims and the assignment of appropriate resources, and, given the glut of material to sift through, can lead to hit-or-miss results.

In this case study written by Michael Paczolt, learn how Nodal™, Milliman’s web-based predictive modeling and decision-support system, sped up the process and accurately identified 95% of high-cost claims for IRMA before they happened, reducing costs by over 15%.

Solvency II risk-free rate curve review

Solvency II came into force on 1 January 2016. The agreed Pillar 1 quantitative requirements set a market-consistent valuation framework for the valuation of assets and liabilities, as well as sufficient holdings of capital to withstand a combination of so-called ‘1-in-200-year’ Standard Formula (SF) stresses. There is no doubt these fundamental principles are set in stone but nonetheless there have been ongoing changes to the detailed rules since their introduction. This was planned from the outset with certain powers given to the European Insurance and Occupational Pensions Authority (EIOPA) to review methodology and assumptions over time, as well as a specific milestone for the European Commission (EC) to review elements of the Standard Formula in 2018, followed by a more holistic review of the entire rulebook by 2021.

Any changes are intended to reflect developments in the insurance sector and the wider environment. These changes could have significant impacts on individual companies and firms may need to reassess their capital management strategies.

This report by Milliman’s Karl Murray, Eamonn Phelan, and Bridget MacDonnell revisits the rules in specifying the risk-free rate term structure, which forms a fundamental part of the calculation of Technical Provisions (TPs). In particular, they analyze changes to the Ultimate Forward Rate (UFR).

New Milliman study reveals favorable results for life/annuity and LTC combination products

Milliman announces the results of a first-of-its-kind, industry-wide study that examines insurers’ experience with combination products – those that couple life or annuity policies with Long-Term Care (LTC) or Chronic Illness (CI) riders.

The study, which includes data from 11 insurers (ten using life insurance-based plans and one using an annuity chassis) focused primarily on incidence rates, lapse / surrender rates, and mortality rates. Policies with LTC accelerated death benefit (ADB) riders and no extension of benefit (EOB) riders comprised about 60% of the exposures, while policies with CI ADB riders represented about 25% (none of which used the discounted death benefit approach); the remaining 15% of exposures were based on policies with both ADB and EOB LTC riders. All policies in the study accelerated the death benefit on a dollar-for-dollar basis.

Combination products are a growing segment in the marketplace, and there’s a need within the industry to begin to measure insurers’ experience. Study findings point to better-than-expected results for participating companies, information which can be used to inform key decisions in the product space.

Key findings of the study include:

• Overall, incidence is significantly better than expected. The actual-to-expected (A:E) is very low when measured against stand-alone LTC assumptions and also lower than when measured against combination product assumptions.
• Plans with extension of benefits have relatively higher incidence than acceleration of death benefit only plans, but results are still favorable.
• Mortality results were somewhat lower than industry experience on stand-alone fully underwritten life products, despite the less extensive underwriting done on some of these combination products.
• Lapse rates by count and amount were generally between 2% to 3% for ADB-only policies. Policies with ADB and EOB coverage were slightly lower, but still higher than seen in the stand-alone LTC market.
• Another major factor affecting lapses overall is the type of base plan. Some differences between universal life, whole life, indexed universal life and variable universal life may be partly explained by equity market performance during the exposure period.

Given the length of time for claim termination experience to develop, the study includes a few early indications of claim termination experience, but does not provide a full and detailed analysis. Milliman plans to update this study again in 2019. Detailed study results are available for purchase from Milliman for a fee.

For more information, click here.

Renting vs. buying vs. sharing: A five-year housing scenario (infographic)

When it comes to purchasing a home, not everyone is financially able to do so through a mortgage with 20% down. And not every mortgage is structured the same way. One of the biggest decisions potential homeowners face is if and when to jump into the pool of mortgage debt, and which way to do so.

In this article, Milliman’s Madeline Johnson considers three defined dwelling paths for borrowers: renting, buying a property with a traditional low down payment mortgage, and buying a property using a shared-equity (also known as shared appreciation) mortgage. The article and infographic below examine how these three paths (rent vs. buy vs. shared equity) compare in a real-life scenario. Using historical data, we can evaluate how the risk of home price decline in a shared-equity arrangement compares to using a traditional mortgage program, or renting, and how the rent versus buy decision can help prospective borrowers understand the potential impact of buying a home on their long-term finances.

Volatility Adjustment considerations under Solvency II

The VA is one of the Long-Term Guarantee (LTG) measures under Solvency II which aims to ensure the appropriate treatment of insurance products with long-term guarantees. However, the VA also affords applicability to other types of products with long-term liability cash flows and one of the aims of this paper is to reexamine the potential for companies to use the VA for their businesses. In this paper, Milliman’s Karl Murray and Eamonn Phelan examine the features of ongoing risk management with regards to the application of the VA.