Workers’ Compensation Underwriting: How Automated Tools Are Changing the Game

Underwriters and actuaries are under constant pressure to meet demands for increased efficiency and innovation. Though there are more data sources than ever, determining how best to balance data insights with underwriter expertise remains a challenge.
Where should risk management teams direct their focus?
How can underwriters achieve consistency?
Workers’ compensation presents unique complexities. With regulatory processes and large risk rating options that vary by state, workers’ compensation pricing creates an additional gauntlet of details that even experienced underwriters may struggle to manage. The need for comprehensive documentation means underwriters today are facing an uphill battle: how to efficiently make meaningful use of data to improve judgement, not cloud it.
In order for an underwriter to effectively do their job, they need automated workers’ compensation tools that provide quality benchmarks helpful for schedule rating credits and debits, retrospective rating, and large deductible plans. These insurance-specific tools help underwriters and insurance entities improve efficiency and provide data-driven documentation for compliance.
Here are three areas where automation can be a game-changer.

Large Risk Schedule Rating

Because large risks are big enough to be schedule rated, underwriters have ranges available to develop premiums. Large Risk Schedule Rating tools are a comprehensive, data-driven solution that can be utilized to assist underwriters with schedule rating debits and credits. These tools provide the following key features:

  • Consistency with company’s approved program
  • Insights on a particular risk relative to the average risk contemplated in the bureau rates
  • Data-driven results for underwriters
  • Built-in documentation 

Retrospective Rating

For risks who elect to have their premiums based on their actual loss experience during the term, underwriters will need to determine the initial premium and all the necessary parameters that will apply at future adjustments.
Retrospective Rating tools help support workers’ compensation underwriters in the following ways:

  • Calculate the basic premium for retrospectively rated policies
  • Allow for flexible user inputs
  • Comply with plan rules and company guidelines
  • Provide built-in documentation 

Large Deductibles

Large Deductible tools provide benchmarks to supplement underwriter judgment and include documentation for the underwriter’s files. Below are some advantages of using this automated solution when developing large deductible workers’ compensation plans:

  • Ability to develop multi-state large deductible premiums
  • Ensure compliance with approved plan rules and company guidelines
  • Availability of built-in documentation

Automation Tools Support Underwriters

Underwriters are essential to risk evaluation. Their experience, discretion and judgment are an important part of the process. These automation tools use data to inform underwriters on the risk and allow them to focus on the aspects of their job that require their expertise. Additionally, they provide a level of control and consistency to workers’ compensation underwriting that offers peace of mind in the event of an audit or other examination.
Workers’ compensation pricing will always remain an important task for underwriters. However, smart automation puts another helpful tool at their disposal.

Perr&Knight’s Automation Tools

During our decades of actuarial consulting for the insurance industry, Perr&Knight’s experts have built workers’ compensation rating tools for the industry with all the features mentioned above.  We have also added custom configurations unique to each program and jurisdiction so that the tool is consistent with approved rules and company guidelines.
In addition to tailoring the tools for each program, our actuarial consulting teams can update the tools to track alongside industry approvals and workers’ compensation metrics. Our experts are also on-hand to add new enhancements as programs change. These updates ensure the tools keep pace with industry experience.
Contact the experienced actuarial support teams at Perr&Knight to discuss how automation can support your workers’ compensation rating process.

Digital Transformation: Old Wine in New Bottles?

So much of what we find new and exciting requires what we too often write off as outmoded.
Today’s insurance technology initiatives are increasingly motivated by our latest term of art, digital transformation. We love to throw those words around as if they represent some magical incantation that, when invoked, will produce brilliant solutions that lift us to otherwise unattainable competitive positions, as masterworks of art that evoke feelings of awe eons after their original creation.
Of course, we’ve been “digitally transforming” for decades. Setting aside the nineteenth-century innovations of Charles Babbage for a moment, modern “digital” computing is easily traced at least as far back as 1945 with the introduction of ENIAC, “the first programmable, general-purpose electronic digital computer”.[1] The intervening years have seen a remarkable explosion of computing power. Famously, the Apollo Guidance Computer (AGC) used to put men on the moon in 1969, with its 2 MHz CPU speed, had roughly the same computing power as a twenty-five year-old Nintendo Entertainment System (1.8 MHz). An old iPhone 4 (2010), with its 800 MHz CPU speed, outgunned the $32 million Cray 2 supercomputer (1985) by a factor of three (244 MHz).[2] And today’s iPhone 12 (2.99 GHz) and Sony PlayStation 5 (3.5 GHz) make those computing milestones seem quaint.
The growth in computing power, and therefore the number of practical applications that can be handled by affordable computers, has been astonishing. Indeed, it has made the aspirations of computer scientists who only dreamed about artificial intelligence and virtual reality just a few decades ago – dreams because they would require rooms full of very expensive hardware – available to the masses in tiny packages for very modest sums.
So it follows that today when we hear about insurers wishing to undertake digital transformation initiatives, we understand that their desire is to leverage today’s massive computing power to gain a competitive advantage. Otherwise, we’re simply talking about modernization, which was all the rage way, way back in 2015. Today’s initiatives have the far more ambitious goal of producing novel solutions, in the sense that competitors haven’t yet discovered – let alone adopted – them, and so they’re in a very real sense disruptive.
But disruption comes out of tolerance for mistakes. Disruption comes from having the wherewithal to experiment and fail repeatedly. Disruption comes from having the courage to engage in radically candid conversations laced with dissent and debate. So disruption can only happen if the company culture permits it to happen – an idea antithetical to an insurance company’s traditional mission, which is to avoid undue risk.
This frosty bit of insight begs an entirely different approach to insurance company operations that goes well beyond technology. Famously linear thinkers, insurance professionals have historically worked to place a price x on some risk y in anticipation of a positive return z. We press this button and that happens. Of course, this approach has turned out to be of dubious value, evidenced by the prevalence of combined ratios that exceed the century mark. Instead, a confluence of factors in a variety of dimensions conspire to destroy our bottom lines, if not our innocence: Geopolitics. The environment. Social movements. Generational sensibilities. Competitive moves. Regulatory constraints. Human psychology. Solar flares?! And yes, the rapid pace of technological change. After all, how popular was cyber insurance – arguably influenced by each of those factors – in 1950?
Woke (forgive me, but the term seems to work in this context, too) insurers have accepted this. And so their efforts are directed toward aggregating not just traditional datasets that populate rating algorithms or underwriting rules, but those many ancillary bits of information that influence risk selection and loss potential in a far more informed (read: non-linear) way. They utilize Big Data. They leverage artificial intelligence. They employ dedicated predictive analytics units. They automate routine operational processes. They invest in new technology. And they adopt change management programs to support those initiatives. That’s a long list of expensive undertakings for a smaller insurer. But that’s the world in which they have to compete.
Middle-tier regionals with relatively modest means must contend with tiny upstarts with tens of millions in capital investment unburdened by years of legacy operations on one end, and multi-billion dollar behemoths spinning off autonomous innovation centers on the other, for their share of the hundreds of billions of premium dollars blown skyward by the shattering of preconceived notions.
And so we arrive at the intersection of culture and technology, of art and science, of hard skills and soft skills. In an industry famously fixated on risk avoidance and profit margins, this juncture becomes an especially challenging moment in time. Indeed, a quick review of recent literature on disruption in the insurance industry makes scant mention of the behavioral changes that must accompany any radical innovation, both within an organization among its constituents and outside among its customers and suppliers.
The impact on many well-established insurers? InsureTech startups are eating their lunch. That is, unless those veteran organizations were prescient (and well-capitalized) enough to develop their own skunkworks, separate and apart from their core organizations in order to permit the risk-tolerant cultures found in their more nimble adversaries. That’s fine if you’re a major player, one of the billion-dollar insurers who can afford separately funded venture arms, or an agile start-up with fifty million smackers to burn. But what of the middle tier, those thousands of regional insurers vying for market share in the face of old threats (mainstays) and new (InsureTechs)?
The obvious answer is they need to think a little differently. With no discretionary trove of millions to casually deploy, the focus must be on manifesting beneficial change. And beneficial change begins with vision, culture, and leadership – not bits and bytes. Old wine in new bottles, you might say.
I’m not suggesting plastering office walls with poster-sized admonitions to “embrace change,” nor am I suggesting that beneficial change is a thing that happens if you hire the right consultants. I am suggesting, however, that with all of the marvels of technology available in the twenty-first century, it’s still people who matter most. It’s still paying attention to what motivates – inspires – every individual responsible for the welfare of the organizations in which they toil that separates leaders from laggards. And most importantly, it’s regularly respecting and acknowledging their contributions to ensure they stay focused and motivated, long after the paint is dry on that beautifully executed automation project.
Of course, standard “tactical” practices for operational improvements and technology deployments involving proven toolsets for workflow analysis, business process design, and technical project management are essential for a successful digital transformation initiative. But no amount of funding will replace the unbridled enthusiasm of a group of colleagues setting out to effect change for the better. It’s that enthusiasm and commitment that drive organizations to prosperity; it is rarely prosperity – and never technology – that drives individuals to become enthused if they’re not adequately engaged and committed to the work they do.

Contact Perr&Knight to support your digital transformation initiative with experienced project managers, business analysts, and process improvement experts well-versed in the ‘people part’ of transformation, who can assist with the requirements management, process redesign, and change management capabilities that are essential for any such project.

[1] Swaine, M. ENIAC. (n.d.). Britannica. Retrieved January 25, 2021 from
[2] Routley, N. (2017, November 4). Visualizing the trillion-fold increase in computing power. Visual Capitalist.

Predictive Analytics Provide Big Gains for Small Insurance Companies

It is no secret that the amount of data in the world is expanding at an extremely rapid pace, and in a time where business is being conducted online due to COVID-19, this rapid data production is going to accelerate more than ever. Of course, this mass influx of data is only useful to companies when they have access to it.
This data gap between insurance companies will widen even more due to COVID-19 as large companies with direct-to-consumer online platforms will see increased business due to stay-at-home orders and less in-person business. The increase in online business could be used in predictive models to analyze marketing trends and gain new market share, which leads to more business to enrich pricing and claim triage models, which increases profits and the ability to gain market share. From there, the cycle will start all over again.
A large data gap already exists between large and small companies, and now the gap for online business capabilities is also growing at an increasing rate. What can small companies do to help make sure that gap does not become insurmountable?
Luckily, external data is now more readily available and easily accessed than ever before. Companies with little data (or in some cases even no data) can take advantage of external information for predictive modeling. Some examples of external data sources include:

  • Government information such as census demographics, weather databases, occupational statistics, geospatial, and property tax information.
  • Numerous industry statistics and services from advisory organizations such as ISO, NISS, or NCCI.
  • Industry information from publicly available rate filings and financial statements.
  • Quote comparison services for competitive analyses.

Misconceptions about small companies’ ability to use predictive analytics are not limited to data constraints. There is also a common misconception about the models themselves having to be extremely sophisticated. While it may be true that many companies are using such complex models, smaller companies can still benefit from the use of analytics by simplifying their scope to accommodate less data. Some examples include:

  • Creating models that assist with monitoring programs by ranking predictors with the largest impact on results. These give quick insights to help focus additional research.
  • Using simpler assumptions and grouping variable levels in order to increase the credibility of the model.
  • Combining company data with external data sources to add additional predictors to your results.
  • Consulting with industry experts to follow modeling best practices such as removing data outliers and/or missing values in order to maximize the amount of usable data and not skew results.

Not only can these scenarios be applied today to help insurer performance, but Perr&Knight has experience in assisting clients in each and every one of them. With both experienced predictive modeling personnel and industry expertise in virtually all lines of insurance, Perr&Knight is uniquely qualified to assist small companies in implementing predictive analytics to help improve insurer performance and profitability.
As the world continues to evolve technologically, so too does the sophistication of insurance products and the insurance process. It is important for small companies to modernize their approaches to help minimize the data gap in an increasingly data-driven environment.

Leverage the power of predictive analytics. Contact the experts at Perr&Knight to learn more about how your company can use data from predictive analytics to improve business outcomes.

Predictive Modeling: 5 Benefits of an Independent Review

The practice of predictive modeling is a powerful tool for risk assessment for today’s insurance industry. What once was considered a new technique for insurance pricing is now getting utilized in all aspects of the industry.
Your models are only as sound as the industry knowledge that goes into their development. Lack of complete regulatory support for predictive models has slowed InsurTech companies and carriers on their path for regulatory approval.
Instead of dealing with the expensive and time-consuming fallout of stalled approvals, it makes more sense to get ahead of potential pitfalls by investing in an independent review of your model from experienced insurance actuarial consulting experts.
Here are five reasons an independent review of your predictive model is worth the investment.

1. Discover your model’s strengths and weaknesses

Independent review from actuarial consulting experts will reveal areas where your model can benefit from improvement as well as verify its biggest benefits. A review that combines proven industry benchmarks with professional actuarial judgment will surface erroneous assumptions, incomplete support and lead to model improvement.

2. Comply with state regulations

Many predictive models have been rejected by state insurance departments due to lack of compliance in that jurisdiction. States have their own unique regulation and you want to be prepared. By partnering with an independent reviewer who knows the nuances of each state’s regulatory process, you’ll strengthen your chance of approval.

3. Strengthen your case with key decision-makers

Achieving buy-in from the customer is crucial when marketing an InsureTech predictive model to insurance carriers. Though your model may perform impeccably, if your company has a limited track record in the insurance industry, it may be a hard sell to the carrier’s executive team. Getting an independent review with comprehensive documentation will demonstrate to decision-makers that your product has been carefully evaluated by insurance industry professionals. This vetting of your model and accompanying written proof may be the deciding factor between your product and a competitor’s.

4. Increase your speed to market

Presenting your model to regulators without thorough pre-submission scrutiny may reveal surprise shortcomings. Discovering these deficiencies while your model is deep into the review process adds unnecessary time. It’s much smarter to pressure-test your model before submitting to state insurance departments to speed up approval for your model’s implementation.

5. Trust in your results

Your data may support strong predictors used in your model, but to be truly effective, results must be combined with subject matter expertise. Insurance experts who understand all steps in the insurance process give you insights for model improvement.
High level assessment of your model’s viability, paired with detailed scrutiny from subject matter experts who specialize in insurance, is a smart way to protect your investment. An independent reviewer will ask tough questions, and follow best practices for predictive modeling in order to assess your methodology to add credibility and strength to your work product. It’s like investing in “insurance” for your insurance product.

Get your independent predictive model review today! Perr&Knight’s experienced actuarial consulting team can help.

Predictive Analytics and Insurance Regulation: 5 Tips for Success

As the influence of big data continues to rise, insurers are utilizing analytic models more often than in the past. But when launching new predictive models for use in insurance programs, it’s never a good idea to submit your model to regulators without the right support. By applying a regulatory-focused strategy, you can ensure that the review process does not slow down your model implementation.

Here are our tips for success:

Tip 1. Prepare thorough data documentation

The models you create for use in your insurance programs will be reviewed by regulators. Make sure your documentation on the data used in the model is clear and thorough, such as disclosure of internal and external data sources, data quality and accuracy checks, handling of missing data fields, as well as any adjustments you made to the data, including capping, removing outliers, etc. Regulators want to be sure best practices are followed by the modeler who conducted the analytics. To ensure that your data documentation is clear, it’s beneficial to contract an outside actuarial consulting firm to conduct an external review of your analytic model prior to submitting to state insurance departments.

Tip 2. Provide strong analytic support

Once you have documented your data, you still need to provide regulators with model validation results. Did you follow best practices when generating your predictive analytic model? A thorough regulatory review will require analytic support such as correlation and interaction tests, the statistical significance of results, confidence intervals, lift charts and many other items. Someone familiar with the regulatory review of predictive models can help ensure you are prepared with the necessary support. Once again, this is another area where it’s smart to partner with an actuarial consulting firm to confirm the accuracy of your results and conclusions.

Tip 3. Be prepared for variations by state

Remember that states may require different levels of support for regulatory approval of an analytic model. Some states have questionnaires as part of the filing process for predictive analytics models. Do all of your data fields comply with state-specific rules regarding allowable data fields? Never assume that just because your submission went smoothly in one state that you can count on an approval in another. If you’re submitting in multiple states, a third-party consultant can save you from major setbacks by performing a compliance review of your model before you submit.

Tip 4. Adopt the regulator’s perspective

Take the time to anticipate the areas that regulators will watch closely. Consider questions and concerns they might have and address them upfront in your support. This will help you stand a better chance of fast approval. If you do have questions about how to best support your model, request to discuss these concern with regulators prior to submitting your model.

Tip 5. Predictive analytic support versus intellectual property

It’s understandable that when you invest so much work and so many resources in developing your model you don’t want to share your valuable intellectual property with the world.  Whether you have developed your predictive model in-house or are using an InsurTech vendor’s model, you need to balance regulator review with protecting proprietary formulas. Partnering with a consulting firm that is familiar with confidentiality requirements can help protect your work without slowing the approval process.
When it comes to predictive models and insurance regulation, the most important thing to remember is: be prepared. Make sure your documentation clearly outlines your predictive analytic process to support the use of the model and address any state-specific regulatory concerns. It’s in your best interest to have all pertinent information at the ready so the process proceeds as smoothly as possible.

For more information about how Perr&Knight can provide predictive analytic consulting services to help you navigate the regulatory process, contact us at (888)201-5123 x3.

How to Use Predictive Modeling to Increase Profitability

Predictive analytics is the practice of extracting information from existing data sets in order to determine patterns and predict future outcomes and trends. Insurance companies can use these sophisticated tools to increase accuracy in risk selection, pricing, and claims handling. With proven models and expert interpretation, carriers are more equipped than ever to make intelligent business strategy decisions that raise revenue and lower costs.
Here are some of the ways the use of predictive models has been proven to help insurance companies enhance their profitability.

To write or not to write

Deciding which risks to write and which to avoid was once an art. With predictive analytics, it’s now a science. The use of predictive models eliminates the guess-work that arises when a company must decide whether to write a particular demographic or whether it makes sense to try to offer a competitive product that is trending in the marketplace. Predictive models can compare data from various demographics, locations, weather, crime statistics, previous claims and other touch points that reveal an accurate picture as to whether each risk is worth writing. Understanding this before binding policies can generate significant savings by not heading down the path of unsuccessful products.

Provide the best match of dollars into risk

Pricing models help insurance providers segment the market on an astonishingly detailed level, accounting for hundreds of variables that were not able to be measured with such a high degree of accuracy in the past. Equipped with this information, insurance companies can develop pricing strategies for their products that reflect the true value of the risk they are covering.

Monitor dollars out

Insurance carriers can also enhance their profitability by improving the claims handling process. Predictive models help identify and reduce fraud and slow down claims leakage. By relying on predictive modeling, companies can be sure that they’re paying claims at the right cost. These tools provide additional accuracy that improves claim assignment to claims adjusters to get the right experience needed for the type of claim, thereby helping with the company’s bottom line.

Available to all

Many insurance companies lack the capital to support an entire predictive analytics department and therefore feel that this resource is beyond their reach. However, actuarial services companies like Perr&Knight understand the tremendous value offered by these models and provide these services for companies who want to increase profitability and compete on a scale with larger insurance providers.
For companies that have never undertaken any type of predictive analytics, we recommend reaching out to third-party support services to discover previously unseen opportunities available through the use of predictive modeling. Actuarial services companies with predictive analytics departments have extensive experience running insurance models on relevant data, integrating outside data and providing the results of the analytics in a usable format that clarifies decision making.

An ongoing strategy

For best results, it’s very important to note that predictive modeling should be applied on an ongoing basis. It’s not a “one-and-done” process. Companies should look for early indicators of marketplace change and be proactive about adjusting pricing and claims handling strategies. By staying on top of these fluctuations with regular monitoring, insurance companies can not only increase profitability but can maintain their edge over time.
Predictive analytics reduces the risk in the risky business of insurance. With the vast amount of data pouring in today, many companies realize the advantage of letting high-powered computers synthesize information with lightning speed. Once the computers have run their algorithms, actuarial services staff can apply their valuable expertise to interpreting the results. This is not only a more efficient use of manpower, but it frees up staff to focus decision making on additional profit-enhancing strategies.
If you would like to learn more about how predictive analytics can help your company, contact Perr&Knight at (888)201-5123 x3 and we’ll outline all the ways that predictive modeling can enhance your organizations’ profitability.

Predictive Analytics: Why You Should Care

Insurance companies have long based their estimates and decisions on analyzing data to help predict future events. However, with increasingly available data and faster processing power, more sophisticated algorithms designed expressly for the insurance industry can be used to augment their data analytics. By applying machine learning and modeling algorithms to historical data patterns, insurance companies now have a more powerful tool set to anticipate future outcomes with greater accuracy than ever before.
The results of predictive analytics for insurance can yield immediate improvements across your entire operation. Whether you are just starting to apply predictive analytics or you are already using it for multiple areas of your business, predictive analytics can help you:

Remain competitive in the marketplace.

More and more insurance companies are adopting predictive analytics to increase profitability and gain an advantage over competitors. Smart companies are already harnessing predictive analytics tools to select risks and price accurately. Therefore, the gap continues to widen between companies who are maximizing their data usage and those who are being left behind.

Make data-driven decisions more quickly.

By advancing your analytic capabilities through the use of sophisticated algorithms, you are using current technology to its fullest capability. This enables your team to base conclusions on accurate and reliable analytics and accelerate data-driven decision making.

Become more proactive.

Traditional data monitoring methods require a tremendous amount of time to uncover patterns and take necessary corrective steps. Even while working at maximum speed, your teams are still reacting to issues as they arise. Once in place, predictive analytics enables your team to anticipate issues and make decisions before they become full-blown problems. Monitoring of predictive models allows for proactive action as your business changes.

Create more accurate pricing and underwriting structures.

This is where most companies are already using predictive analytics: to better segment their business and develop more accurate pricing. Rely on predictive analytics to a greater degree, and ensure that your company is charging the correct price relative to risk.  By running quality data run through a reliable predictive analytic model, you are giving underwriters a tool to better select desired risks and achieve greater precision in discretionary pricing.

Detect fraud faster.

Appropriately developed algorithms can highlight anomalies in data, increasing the speed in which your claims department can reveal fraud incidents. This reduces the number of fraudulent payouts and immediately improves your bottom line.

How to get the most from your analytics model

Models can never replace the expertise of an experienced underwriter but they make the job more efficient and improve results.  However, the biggest mistake we see insurance companies make is not soliciting upfront input and feedback from the end users – the underwriters and agents who will be expected to use these models. If developed correctly, predictive analytic models can become invaluable tools that enable teams to do their jobs faster and more accurately. Involve your end users in meetings with your predictive analytics development team to ensure that the model captures and interprets the data which will be most helpful to your organization.

The importance of maintaining data quality

Analytics are only as reliable as the quality of data they capture. Because effective predictive analytics models use very detailed policy and claim information, be sure to work with a company who has expertise in the insurance field and understands the significance of certain anomalies. When you evaluate your data capture in detail, you can improve your data quality moving forward.
The power of predictive analytics for insurance is not limited to the pricing and handling of the insurance product. Once the correct tools are in place, predictive analytics can improve many other internal and ancillary aspects of your insurance company’s business. Finance departments can apply predictive analytics to collection strategies. Human resources departments use analytics to narrow down a range of potential candidates, selecting those with desirable characteristics that will best support the company. Marketing departments can use predictive analytics to gauge the effectiveness of communications, increasing marketing ROI. The applications of predictive analytics for insurance can extend as far as the questions you ask about how to advance your business.
If you would like to enhance your insurance business and develop more powerful models for pricing, reserving, underwriting and/or internal operations, contact us at (888) 201-5123 Ext 3. Our predictive modeling experts can help you develop solutions that apply analytics to boost your company’s performance.