Sponsored Content by Milliman

The Evolution of Analytics

Better tools, more data and more computing power mean that actuaries and insurers can apply predictive analytics in new ways.
By: | September 19, 2017 • 6 min read

Predictive analytics are not new.

The term gained traction in recent years, riding the wave of Big Data, but actuaries have been using predictive modeling techniques such as GLMs and decision trees for at least 20 years.

Advancing technology and new data sets, however, have allowed predictive analytics to evolve in sophistication.

“What was called ‘data mining’ in the 1990s was renamed ‘analytics’ in the 2000s, and as new technologies and methods for data storage, preparation, and visualization emerged in the 2010s, this field of work has been rebranded again as ‘data science,’” said Peggy Brinkmann, Principal & Consulting Actuary, Milliman.

The Evolution of Analytics: Although the buzz words have changed (data mining, analytics, data science), they are all related and have built upon each other as our data, technology, and analytic methods have evolved over time.

“We’ve seen an evolution of greater granularity and richness of data, new sources of data, and more cost-effective technologies for storing, processing, and analyzing that data.”

Better tools, more data and more computing power mean that actuaries and insurers can apply predictive analytics in new ways, such as tailoring claims management approaches based on predicted outcomes, building more detailed risk assessments, and more accurately pricing risk.

Some key areas that predictive analytics are changing the way insurers do business include:

1. Claims

Peggy Brinkmann, Principal & Consulting Actuary

More sophisticated predictive tools allow earlier identification of an insurer’s most and least expensive claims.

“Identifying low cost claims early allows insurers to perhaps reduce the resources that would typically be dedicated to that claim. Those extra resources can then be re-directed to high cost claims,” said Philip Borba, Principal, Economics Consulting, Milliman.

Borba uses machine learning techniques that starts with a long list of characteristics and then proceeds to identify the characteristics that have the greatest influence on distinguishing claim costs, recovery opportunities, and other claim-management outcomes. These machine learning techniques often end with a “claim score,” not unlike scores used in other industries. Also, some of the characteristics are coming from data that were underused in the past. Text-mining allow insurers to dig deeper into claims data to glean new and valuable information from existing data sources — primarily, medical reports and adjusters’ notes.

Those notes contain clues that indicate whether a claim is likely to be high or low cost.

“Historically, you wouldn’t know that a surgery was involved in a claim until you got the bill for it six weeks later. But the adjusters probably talked about the possibility of surgery in the first few days after the claim occurred,” Borba said. “We now have the software to go through the adjusters’ notes and pick out these clues that indicate that this may be a serious, high cost claim.

Fifteen to 20 years ago, the computing power did not exist to efficiently comb text for key words or patterns. It was all done manually — a time-consuming endeavor. More powerful computers and text mining software solutions mean that actuaries can categorize and predict potential claim outcomes as early as 30 days in.

“This is a bit of a sea change, because we’re no longer looking at claims that are five to 10 years old and retroactively making the connection that those involving surgeries or attorneys were high cost claims,” Borba said.

“Now we can do that within a month, but using different data.”

2. Driving Safety

Philip Borba, Principal, Economics Consulting

Vehicle telematics provide detailed insight into the specific drivers or driving behaviors that contribute to losses. As auto claims costs skyrocket, tightening up loss prevention is a major focus for fleet managers.

Some individuals and fleets opt to install telematics devices directly into their vehicles, but those units are costly. Another popular option is to have drivers download a smartphone app that can decipher if and when the driver uses his phone while on the road.

“The app won’t monitor who you’re calling or texting, what you’re saying, or what other apps you may be using, but it can determine when the phone is in use,” Brinkmann said.

That data is invaluable as distracted driving increasingly contributes to accidents.

“We’re continuously using machine learning to process this data and benchmark our models, and to help us identify the weak points in the generalized linear models we use for auto risks,” Brinkmann said. “For pricing applications, you don’t necessarily see the machine learning in the final model, but we’ve used it in the background to adjust the model to be as predictive of loss as possible.”

Data collected via telematics can actually replace traditional auto underwriting variables, like age, gender, and garaging location.

“Not everyone in each of those groups has the same risk. By collecting more data on drivers, we can go deeper and find the points of differentiation in their risk profiles,” Brinkmann said. “The more data we accumulate, the more granular we can get.”

3. Property Risk

Data and machine learning can provide similar granularity on property risk — specifically, susceptibility to natural catastrophe like flood or hurricane.

“We can look at specific latitudes and longitudes, relative elevation and distance from a river or coast. For hurricanes, we can look at information about land cover, because surface roughness affects your hurricane risk,” Brinkmann said. “The likelihood that your property will be damaged by a sinkhole depends on variables like the soil permeability, population density, and ground water level of the location.”

That level of detail in geological and geographic information did not exist in the past. A more specific and individualized view of risk lends itself to more tailored underwriting and more accurate risk pricing.

4. Competitive Rating

Risk pricing that is more closely tied to loss experience also gives insurance carriers a clearer view into their competitive standing in a given market.

“When you propose redoing rates for a company to better reflect their cost of risk, their first question is usually, ‘How does this impact my competitive standing?’” Brinkmann said.

Working with comparative rating engine vendors, Milliman can show clients how their rates stack up against competitors within their market segment. Clients can access the data themselves to see how a change in their competitive positioning impacts a particular book of business. Or if they want to enter a new market or launch a new program, for example, they can see what the average rates are and whether it could be a profitable market for them.

“That allows you to either get rid of risks that were badly priced or adversely select risks against your competitors that you can write at a more competitive rate,” Brinkmann said. “I call it descriptive analytics. I’m not predicting what their outcome will be, but the data the analysis enabled by machine learning helps them sift through all of this information and identify these segment definitions that are useful to their business.”

“There’s nothing like having solid data to guide your decision.”

To learn more, visit http://us.milliman.com/us/solutions/analytics/.



This article was produced by the R&I Brand Studio, a unit of the advertising department of Risk & Insurance, in collaboration with Milliman. The editorial staff of Risk & Insurance had no role in its preparation.

Milliman is among the world's largest providers of actuarial and related products and services. Milliman serves the full spectrum of business, financial, government, union, education, and nonprofit organizations. In addition to our consulting actuaries, Milliman's body of professionals includes numerous other specialists, ranging from clinicians to economists.

Business Interruption Risk

Hidden Risks of Violence

The Las Vegas shooting and other tragedies increase demand for non-physical damage BI coverages. The market is growing, but do new products meet companies’ new needs?
By: | December 14, 2017 • 5 min read

Mass shootings in the United States and the emergence of new forms of terrorism in Europe are boosting demand for insurance against losses caused by business interruption when a policyholder suffers no direct property damage, according to insurers.


But brokers say coverage for non-physical damage BI (NDBI), needs to evolve to better meet the emerging needs of corporate clients.

For years, manufacturing clients sought a more comprehensive range of NDBI coverages, especially due to the indirect effects of natural catastrophes such as the Thai floods that disrupted global supply chains in 2011.

More recently, however, hospitality and entertainment companies are expressing interest as they strive to adapt to realities such as the mass shootings in tourism hotspots Las Vegas and Orlando and terror attacks in such popular destinations as New York, Paris, Berlin, Barcelona and London.

In addition to loss of life and property, revenue loss is a real risk. Tragedies that cause a high number of fatalities can cause severe financial losses, especially for companies relying on tourism, as visitors shy away from crime scenes.

Precedents already exist. Paris received 1.5 million fewer visitors than expected in 2016, after the French capital was targeted by a series of deadly terror attacks the year before.

More recently, bookings declined in the immediate aftermath of a shooting at the Mandalay Bay Resort and Casino in Las Vegas that took the lives of 58 people on October 1: Bookings at the hotel have since recovered.

Joey Sylvester, national director of operations & planning, Public Sector, Gallagher

“The recent horrific mass shootings in Las Vegas, Nev., and in Sutherland Springs, Texas, raised awareness and concerns about similar events occurring in areas where the public congregates, such as entertainment venues like sporting events, concerts, restaurants, movie theaters, convention centers and more,” said Bob Nusslein, head of Innovative Risk Solutions Americas, Swiss Re CS.

“The second highest NDBI cover to natural catastrophes is terrorism, including active shooter and mass shootings.”

However, products available in the market do not always provide the protection companies would like. Active shooter coverages, for example, focus mostly on third-party liabilities that policyholders may face after a shooting.

Loss-of-attraction policies often define triggering events with a high degree of detail. These events may need to be characterized as a terrorist attack or act of war by authorities. In some cases, access to the venue needs to be officially cut off by police.

It follows that an attack by a 64-year old ex-accountant who shoots hundreds of people for no apparent reason — as was the case in the Mandalay Bay tragedy — isn’t likely to align with a typical policy trigger.

But insurers say they are trying to adapt to the evolving realities of both mass shootings and terrorism to meet the new needs expressed by clients.

“The active shooting coverage is drawing much interest in the U.S. market right now. In Europe, clients are increasingly inquiring about loss of attraction,” said Chris Parker, head of terrorism and political violence, Beazley.

“What we are doing at the moment is to try and cross these two kinds of products, so that a client can get coverage for the loss of attraction resulting from an active shooting event.”

Loss-of-attraction policies cover revenue loss derived from catastrophic events, and underwriters already offer alternatives that provide coverage, even when no property damage is involved.

To establish the reach of such a policy, buyers can define a trigger radius — a physical area defined in the policy. If a catastrophic event takes place within this radius, coverage will be triggered. This practice is sometimes called “cat in a box.”

Some products specify locations that, if hit by a catastrophic event, will result in lost revenue for the insured. For resorts or large entertainment complexes, for example, attacks on nearby airports could cause significant loss of revenue and could be covered by NDBI insurance.

Measuring losses is a challenge, and underwriters may demand steep retention levels. According to Parker, excess coverage may kick in after a 20 percent to 25 percent revenue drop.

Insurers will also want proof that the drop is related to the catastrophic event rather than economic downturn, seasonal variances or other factors.

“Capacity is very large for direct acts of terrorism but lower for indirect terrorism and violent acts because the exposure is far greater,” said Joey Sylvester, national director of operations & planning, Public Sector, Gallagher.

“Commercial businesses, public entities, religious and nonprofit organizations have various needs for this type of coverage, and the appetite is certainly trending upward.”

It is difficult to foresee which events will cause business disruption. As a result, according to Nusslein, companies generally prefer to purchase all-risk NDBI covers rather than named-perils coverage.

“The main reason is that, if they have coverage for four potential NDBI events and a fifth event occurs, the fifth event is not covered,” he said. “Insurers, new to NDBI covers, still prefer named-perils covers over all-risk cover.”

Current geopolitical tensions are also fueling buyers’ demands.

“Many companies want nuclear, biochemical, chemical and radiological exclusions removed from terrorism NDBI covers. While this is more difficult for insurers, it is not impossible,” Nusslein said.

“War risk NDBI cover is becoming more sought after due to political tensions between the U.S. and North Korea.”

“Many companies want nuclear, biochemical, chemical and radiological exclusions removed from terrorism NDBI covers. While this is more difficult for insurers, it is not impossible.” — Bob Nusslein, head of Innovative Risk Solutions Americas, Swiss Re CS

Natural catastrophes still constitute the largest share of perils underlying NDBI products.  Parametric indexes are increasingly employed to provide uncontroversial triggers to policies, said Duncan Ellis, U.S. property practice leader, Marsh.

These indexes range from rainfall levels and wind speed to the measured intensity of earthquakes. Interest in this kind of NDBI coverage expanded after the recent hurricane season.


“The benefit of these products is that you do not have to go through the settlement process, which clients hate,” Ellis said.

NDBI policies are often bespoke, which is more common for very large insurance buyers.

“Usually, the market offers bespoke coverages for individual industries or clients, with very significant deductibles,” said Tim Cracknell, partner,  JLT Specialty.

NDBI cover can also help transfer regulatory and product recall risks. The life science sector is expressing interest in this kind of solution for cases where a supplier goes bankrupt or is shut down by a regulator, or a medication needs to be recalled due to perceived flaws in the manufacturing process.

Experts say that concerns still to be addressed are NDBI losses caused by cyber attacks and pandemics.

Capacity is an ongoing concern. According to Swiss Re CS, $50 million to $100 million, or even more, can be achieved through foundation capacity provided by a lead insurer, with syndicated capacity to other insurers and reinsurers, depending on the risk. &

Rodrigo Amaral is a freelance writer specializing in Latin American and European risk management and insurance markets. He can be reached at [email protected]