Transforming the insurance claims life cycle using analytics

Let’s be honest, the financial results of most insurers in 2011, especially Property & Casualty,  were….well disastrous. Higher combined ratios were predominately a consequence of increasing loss ratios, hence improving the claims process must be a high priority for insurers. One way to do this is to use predictive claims analytics to optimize loss reserves, increase productivity and assist in preventing fraud.

Claims analytics is the process to analyze the structured and unstructured data at all stages in the claims cycle, from First Notice of Loss, to payout, through to subrogation. Rather than analyzing one case at a time - based on only the current information available - analytics gives you added perspective by allowing you to view this one claim “in context” –by comparing it with previous claims settlements in your database.

Previous Analytical Insurer blogs have covered how analytics can help with fraud detection, as well as claims recovery by improving the salvage and subrogation process. But claims analytics is not limited to these areas. Two other opportunities for claims analytics are in claims benchmarking and litigation management.

A major challenge insurers face today is the inability to accurately forecast the loss reverse and ultimately predict the outcome once the claim has been submitted. Using analytics, it is possible to calculate an accurate loss reserve amount and benchmark each claim based on similar characteristics, hence reducing the propensity for loss padding. For example, data mining techniques have helped insurers identify that the size of a claim payout grows significantly based on the number of days between when the claim occurs and when it's reported. In most instances the size of a claim can increase by approximately 50 percent if the insured does not report the claim within the first four days.

Finally, some insurers are beginning to use analytics to calculate a litigation propensity score. Claims that involve an attorney often double the settlement amount and significantly increase an insurer’s expenses. Analytics can help insurers determine which claims are likely to result in litigation, and mitigate those claims to more senior adjusters who can settle the claims sooner and for lower amounts.

Fortunately I am not a lone voice on this topic. I am looking forward to next week’s ACORD LOMA conference, which has sessions from Tower Group’s Karen Pauli on “Next Generation Claims Analytics: Five Areas Claims Executives Must Invest In” and Jose Trasancos from Utica Insurance talking about “Harnessing analytics for Claims”. While at the IASA conference in early June I will be speaking with FINEOS on “The Future of Claims-Optimizing Outcomes”.

For those of you unable to attend these conferences and would like more information about claims analytics then download this white paper on “Predictive Claims Processing”.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Fraud detection a hot topic at SAS Global Forum

This week I had the pleasure of attending SAS Global Forum, the world's largest gathering of SAS users. It was attended by more than 3,500 business and IT users of SAS software and solutions. Along with high-performance analytics, fraud detection was a hot topic.

An insurance fraud ring visualized in the latest version of SAS Fraud Framework for Insurance.


How SAS detects fraud

I presented a whitepaper on Combating Insurance Claims Fraud to a large group of SAS users. During the lively discussion with attendees, a few key themes emerged:

  • Text analytics is a key driver of better fraud detection. Some of the most useful information for detecting suspicious claim activity is in unstructured text sources like claim notes.
  • The ability to deploy a variety of detection techniques in a hybrid approach on a single technology platform is highly desirable.
  • Having access to full administrative tools to modify fraud detection algorithms without having to rely on a vendor or IT resources is a huge asset. Organizations recognize the need to become more agile as they develop their proactive fraud detection capabilities and respond to constantly changing fraud threats.

New software release

In conjunction with the conference, SAS announced a new version of SAS Fraud Framework for Insurance and SAS Enterprise Case Management. Enhancements include streamlined social network analysis, pre-built insurance content for faster deployment, and the new SAS Financial Crimes Monitor – a graphical user interface that streamlines administration of the entire framework and logically manage rules, models and alerts.

During demonstrations of the new software, attendees were focused on some key features. New social networking capabilities include a network hierarchy layout; greater flexibility to merge, hide or remove network entities; and adding annotations, such as text and images. SAS Fraud Framework for Insurance incorporates prebuilt insurance content, such as an extendible data model and industry-specific red flag business rules and models for detecting property and casualty claim fraud.

Real world results

Tim Wolfe, Director, Special Investigations Unit at CNA Insurance gave attendees an overview of the types of results insurers can see when deploying an analytical fraud detection solution. Within the first few months of using the SAS Fraud Framework for Insurance to detect suspicious claims, CNA has already recognized hundreds of thousands of dollars in savings and are well ahead of schedule to exceed their expected return on investment for the project.

The solution has also helped CNA identify and prioritize major case investigations involving suspicious medical providers. More than a dozen such cases with over $15 million in exposure have already been identified. And CNA is leveraging this success as a competitive differentiator in their sales process. Wolfe told the audience, “A couple of large fraudulent claims could put a small commercial insured out of business. Our workers’ compensation insureds want to know that we are protecting them by stopping such claims.”

Finally, the insurance industry seems ready to embrace analytics as a key component of their anti-fraud arsenal. Are you planning on implementing a new fraud detection technology? Tell us in the comments.

James Ruotolo is the Principal for Insurance Fraud Solutions at SAS. Connect with him on Twitter

Post a Comment

What do Insurance and St. George have in common? April 23rd.

Earlier this week was April 23rd, or as it is known in England, St. George’s Day. Since my children are half British, they are always asking about English culture and traditions, such as Guy Fawkes Night. However, when they asked what do you do in England for St. George’s Day, I was disappointed to tell them that we really do not celebrate it. It’s a non-event. In fact, in England these days there are probably more parades to celebrate St. Patrick’s Day than St. George’s Day.

This year, April 23rd also marked some big news for Insurance at SAS Global Forum, the world's largest gathering of more than 2,000 SAS users.

First of all, insurance companies, Chartis and Allianz, were both presented with the prestigious SAS Enterprise Excellence Award.

Chartis was recognized for its use of analytics in three specific areas: executive liability insurance, catastrophe (CAT) modeling and financial accounting. With SAS, Chartis improved profitability through better pricing, expedited refined claims service programs, and enhanced statutory and compliance reporting. For more, read the Chartis success story.

Allianz , the world’s  third largest insurance company, is experiencing improved efficiency throughout its global organization with a centralized business intelligence and analytics solution from SAS. Accepting the award was Dr. Ralf Schneider, CIO of Allianz Group.

Also, announced at this year’s SAS Global Forum was the launch of the latest version of the successful SAS Fraud Framework for Insurance solution.  According to Stephen Applebaum, Senior Analyst at Aite Group, “With questionable claims at all-time highs, insurers need advanced analytics and link analysis to identify and prevent fraud sooner.” Known for preventing, detecting and managing claims fraud across lines of business, SAS Fraud Framework for Insurance increases the efficiency and accuracy of SIU investigations. Read more about the new features and functions of the solution in the Press Release.

Now, everyone knows that March 17 is St. Patrick's Day, Patron Saint of Ireland and you learnt that April 23 is St. George Day, Patron Saint of England.  But did you know that there is a Patron Saint for Advertisers (St. Bernardino of Siena - May 20), Taxi Drivers (St.Fiacre – August 11) , Hairdressers (St. Martin de Porres – November 3) and even The Internet (St. Isidore – April 4). However there is no Patron Saint of Insurance, any suggestions?

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Microinsurance – Why simpler may be better.

A lot of innovative ideas are often a reincarnation of an old concept, and microinsurance is no exception. In the late 19th century, insurance carriers began selling life insurance and burial policies door-to-door, primarily to factory workers. These policies had low premiums representing low sum assureds. This practice continued well into late 20th century. In fact I can remember when I was growing up, the “man from the Pru” coming round to collect the weekly premiums.

The term “microinsurance” originated in the mid 1990’s and is defined as insurance policies with low policy limits and consequently small premiums. Microinsurance is seen as a way to bring individuals out of poverty by providing compensation for the loss of critical life-sustaining elements (e.g., the loss of crops or livestock).

As expected, the growth and opportunities for microinsurance are predominately in the developing countries. But just as important, there are many traits of microinsurance that could benefit the developed countries, one of which is product design.

The simple product design and group-based pricing for microinsurance are easy to understand, especially with first-time buyers. Unfortunately many insurance companies have treated product design like new washing machines. New products are designed with many new features that most consumers are unlikely to ever use.

Let me give you a personal example of the complexity of today’s insurance products. Despite having worked in the insurance industry for a number of years, when I moved to America just over a decade ago, I was amazed at the number of different coverage and limits available. I had no idea how much coverage I should have for bodily injury or uninsured/underinsured motorist and I had to contact an agent to help me through this maze.

The moral behind this example is that today’s first time buyers are the Gen Y’s and Millennials.   They are going to transact most of their business online without best advice or the need for agents to understand the appropriate level of coverage. Hence the insurance company that provides simplified insurance products to better serve this growing profitable customer segment could gain distinct competitive advantage.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

When did Insurance become funny?

Next week is opening week for baseball season and being a big Red Sox fan I cannot wait, especially after how last season ended. As I get excited about watching these games on TV, I have noticed a huge increase in the amount of insurance commercials during these broadcasts. Televised sports programs increased by 16% last year and more importantly, sports programming is watched live by 97% of the viewing audience. With DVR, Netflix, Video OnDemand and shows available via the Internet, most commercial-free, live sports is now proving to be the mecca for advertisers, many of which are insurance companies.

As I watch these commercials, I have begun to ask myself, “When did insurance become funny”? Humor is not something you normally associate with insurance. The basic concept of insurance is to provide compensation in the event of a loss. Whether that loss be damage to a vehicle, theft of personal property or even the death of a loved one. None of these are laughing matters, and yet more and more insurance companies are using comedy as an effective marketing tool. Why? The simple reason is that humor is one of the most effective tools to increase brand awareness, especially with the more youthful audience. Today, the US insurance industry spends over $2.5bn on television advertising. A staggering figure, hence it is important that the message resonates with its target audience.  Also, the use of humor is not exclusive to the US, in the UK they have the Meerkat for insurance aggregator “Compare the Market”. On a personal level, my favorite is Allstate’s Mayhem character, while my children claim I sound like GEICO’s gecko.

However just like when we hear a joke too often, it becomes unfunny, so insurers run the risk that the humor will soon become stale. To help monitor this, insurers are tracking the sentiment of their campaigns through social media with tools like SAS Social Media Analytics. Progressive’s “Flo” is a very polarizing character. It seems that people either love her or hate her. But, more critically she sparks a lot of discussion and debate. Interestingly, Progressive’s Facebook page has approximately 23,000 likes, while Flo’s Facebook page has over 3 million likes. Truly emphasizing the combined power of humor, insurance advertising and social media.

Unfortunately I do not have a crystal ball to predict if insurers will continue to use humor in their messaging. However I do foresee a big parade beginning at Fenway Park in late October. Let’s go Red Sox.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Tell a good story – How imagination can help the Analytical Insurer

There is no question that Analytics is a hot topic. It seems like everyone is talking about it. We have the excitement over its usage in baseball with the whole Moneyball story, through to its usage specifically within insurance.  Analysts, thought-leaders and journalists are all predicting analytics to be the major initiative for insurers in 2012 and beyond.

So to help insurance carriers better understand how they can use analytics, I recently recorded a webinar called the Analytical Insurer. Accompanying me on this recording was two of our customers, Jennifer Golec from XL Insurance and Matt Christensen from AXA Equitable.

Personally I found this to be a fun webinar to record. The three of us had a lively discussion on a number of topics including career opportunities for new analytical talent within their organizations.

I kicked the webinar off by asking the two of them what is their definition of analytics? Jennifer gave a refreshing idea that analytics is part statistics, part programming and part storytelling. I loved this concept. Analytics is not just number crunching or responding to traditional antiquated  KPIs. It’s about using your imagination to think differently. To mine the data to find answers to questions people have not previously asked. In my opinion, this is what the analytical insurer is all about. It has the potential to give insurers that competitive advantage over its peers.

Next both Jennifer and Matt spoke at length about the great benefits that analytics brings to their respective insurance companies, some of which are covered in the white papers Analytical P&C Insurer and Analytical Life Insurer

Of course today, no webinar would be complete without the obligatory question on Big Data. Both of the participants agreed that they were not currently using social media information and other aspects of big data. While there are plans in the future to incorporate this information, currently it’s a matter of maximizing the insight from their existing data. In fact, Matt mentioned that their analytical resources need to “minor” in data management in order to get their predictive models working adequately.

Finally, we discussed how analytics is viewed culturally within the industry. While some insurers have had quick wins with a bottoms-up approach for  long-term success, any analytical initiative must be driven by senior executives. Fortunately both Amy Radin, new CMO at AXA Equitable and Seraina Maag, CEO of XL Insurance, view analytics as important for sustained growth within their organizations.

To hear more about the Analytical Insurer from XL Insurance and AXA Equitable, you can view the webinar at this link.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Ten reasons to invest in an automated fraud detection system

Automated fraud detection systems are becoming more common in the insurance industry as the technology improves and the benefits become more evident.  Many companies have embraced this change and are showing measurable and significant returns on their investment. 

The quantifiable benefits are numerous – an increase in quality and quantity of cases referred to the SIU and an improvement in the impact rate on those cases.  But to truly understand the value of an analytical fraud detection system, companies should also consider the soft benefits even though they may be more difficult to quantify.

Here are ten of those benefits:

  1. Business intelligence - Being able to pull or automate reports from one system to monitor productivity, case diversification, strategic planning and goal setting, resource allocation, workload balancing and to help with regulatory reporting is an overlooked benefit.   Companies spend hours trying to pull information together and then manipulate it to get the type of reports needed. With a robust business analytics framework underlying your fraud detection system, it is easy to create, customize and standardize reports.
  2. Training - The ability to notify an adjuster, manager or investigator that certain data attributes triggered a high fraud risk score inherently trains the user. Seeing why claims are being flagged as high risk allows the adjuster to learn patterns and red flags that might be present on other claims.  This is especially important with newer employees who may not be focused on identifying suspicious claims as they learn the various aspects of their job.
  3. Identification of new trends, fraudsters and claim anomalies BEFORE payments go out - The right detection system will flag anomalous patterns such as high Bodily Injury to Physical Damage ratio in an auto accident or procedure codes not matching treatment plans in a casualty claim. While this analysis can be done on individual claims, a robust fraud detection system can also detect patterns of organized ring or provider fraud. For example, anomaly detection might flag a provider using a more severe diagnosis code than his peers for similar injuries. Adjusters and investigators would have to look through a lot of data and do a lot of manual manipulation to detect that trend.  With the right technology this can be done quickly behind the scenes.
  4. Level the playing field - In a manual process where the company relies on adjusters to identify suspicious claims, there are typically a few motivated adjusters who seem to make the majority of the referrals.  By having a system in place, you can ensure every claim is looked at the same way and find what those other adjusters have been missing.
  5. Improve customer service - By using the hybrid approach to identify suspicious claims and reduce false positives, suspicious claims get referred to the SIU or special handling group and the meritorious claims get paid faster or get to the right claim professional faster keeping the customers happier.
  6. Resource allocation, where are my clams happening and where is my staff located -   Do I need to shift resources to control expenses? Any strategically minded manager looking to use his resources efficiently should be asking these questions. Having the data to see this is powerful.
  7. Global/Enterprise level solution - Many companies have gone through mergers and acquisitions and have several systems or databanks that have various data sets in them, some have subsidiaries or business units around the country or globe for that matter.  Different business units all are trying to keep the profits of the company strong.  Having a truly global perspective of the anti-fraud efforts throughout the enterprise often leads to best practices and knowledge transfer.
  8. Data integration - Bringing in third-party data like public records that may have a predictive value is a big benefit. Data sources with  derogatory attributes like bankruptcies, liens, judgments, criminal records, foreclosures or even address change velocity to indicate transient behavior are all public records that can be integrated into a model. Other types of third-party data would be beneficial in enhancing efficiencies and could include appraisal information to determine if damages match description or loss or injuries being claimed. One of the most underutilized data source is the medical bill review data.  This data, if used in a model properly, is a gold mine for companies investigating medical fraud.  Uncovering anomalies in billing and adding these to the other scoring engines or Social Network Analysis will decrease the amount of time an investigator or analyst spends trying to pull all of the pieces together.
  9. Deterrence – When a company has a systematic approach to identify suspicious claims and then resists the non-meritorious claims, the ethically challenged fraudsters look for other sources of revenue and are going to travel the path of least resistance. This means going to a company that is not able to detect or investigate suspicious activity.
  10. Technology can be expanded to other areas - The technology used to identify suspicious claims can also be used to identify which cases have the highest likelihood of subrogation recovery or which claims can be fast tracked for quicker payment and better customer service.  It can also identify potential high severity claims early in the claim process.

Return on investment, enhanced efficiencies and quality referrals are important to express as benefits to a fraud detection system when deciding to upgrade or purchase a new process or system.  It is equally important to realize there are other benefits not usually discussed when looking at automated fraud detection systems.

I’m Dennis Toomey, Senior Solutions Architect in the Fraud and Financial Crimes Practice at SAS. For further discussions connect with me  LinkedIn or Twitter.

Post a Comment

Better 2nd time around – lessons insurers can learn for Solvency II

In life the lessons of the past often can be applied to the challenges of the future. We learn to crawl which puts us in a good place to learn to walk. We then learn to walk which hopefully puts us in a good place to learn to run. In the business world it is not much different. Lessons learnt previously should be applied into new challenges and this is very true as insurers continue with their Solvency II implementations.

Recent efforts around Basel II by banks have once again confirmed the importance of data management activities, which typically represent around 80% of the work involved. With Solvency II there is an even greater emphasis on the management and quality of the data than was the case with Basel II since Data Quality is recognized within the Solvency II Directive as a critical aspect of good quality risk management practice and calculations.

Unfortunately for many insurers, current data governance, data quality and monitoring capabilities are not sufficient to comply with these new regulations. However, fortunately this does present the first opportunity for many insurers to get to grips with an issue that has long gone unchecked. That is meeting a regulatory challenge with a proactive approach that can yield benefits well beyond just meeting the regulatory requirements. Data Management, Data Quality and Data Governance will become top of mind topics for all insurers and re-insurers in the EU if it is not already!

One organization that did take this opportunity was HDI Assicurazoni. This insurer knew that to compete successfully in the Italian market, not only must they be Solvency II compliant, but they must be focused on providing quality customer service and offering products tailored to the individual customer needs.  HDI Assicurazoni selected SAS Risk Management for Insurance to improve data quality, make faster risk-based decisions and comply with Solvency II. According to Francesco Massari, Head of Information Systems at HDI Assicurazoni, “By using SAS we met the double objective of improving data quality and streamlining processes”.

A good data management strategy is not only a prerequisite for meeting Solvency II regulation, but an excellent one can help insurers increase risk awareness, improve confidence in financial stability, enhance pricing and much more. To learn more about how SAS can help read about Data Management for Solvency II

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Life insurance and analytics – the rewards are high, but it’s not gambling.

Is it considered gambling if you put your money on a certainty? I recently read a survey that found that only 44% of US households have an individual life insurance policy. I found this statistic incredibly surprising. Yes,  life insurance is a discretionary product and in difficult economic conditions is often one of the first cutbacks when one assesses expenditure. However in the immortal words of Benjamin Franklin “In this world nothing can be certain, except death and taxes” so why would anyone not gamble on a certainty. Likewise, life insurance companies that adopt analytics are no longer gambling on uncertainty.

Life insurance does have a reputation for being a conservative industry and a laggard compared to its P&C sister in terms of technology adoption. But that perception is changing. New York Life and other life insurance companies are embracing Facebook as a new marketing and distribution channel and this change is not just restricted to social media. Life insurance executives are beginning to implement analytics as a way to innovate, differentiate and improve their organizations.

The analytic strategies that life insurers can employ are divided into four representative categories

  • Distribution and Producer Analytics: Influencing distribution and producer behavior through loyalty and lifetime value indicators.
  • Customer Analytics: Finding and understanding the needs of your target customers and providing them with the information they need when they want it and the way they want it.
  • Product Management: Supplementing traditional actuarial and underwriting methodologies with predictive analytic capabilities in the product development life cycle.
  • Operations: Identifying ways to optimize the workforce while creating a better customer experience.

There is no doubt that life insurance companies that continue to operate within their status quo business model will be at a competitive disadvantage in the coming years. Increasingly, insurers must provide unique products and services tailored to meet the diverse needs of their producer and consumer communities. To do so, they need a deep understanding of complex customer behaviors, market segments and product life cycles. Fortunately analytics represents the answer that will enable life insurance companies to transition to this new digitalized world.

To learn more about how analytics is transforming both Life and Property & Casualty insurance companies tune into a webinar with XL Insurance, AXA Equitable and SAS on February 29th at 1pm EST. For more information and to register, click here.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment

Disruption in Insurance – Emerging technologies are breaking the status quo

Last week I was fortunate enough to attend one of my favorite events. Celent’s annual Insurance Innovation and Insight Day, which this year took place in Boston.

The general theme of this year’s event was disruption. How emerging insurance technologies are fostering creative disruption in the tranquil world of insurance. These emerging technologies include telematics, fraud scoring, and even social media (see diagram) In fact based on an upcoming research paper by Celent, 59% of insurers responded that they using social media for marketing functions today, and within 3 years nearly all (93%) would be using it.

This event also shone the spotlight on the carriers and vendors with Celent’s annual Model Carrier of the year award. This year Nationwide were recognized for their Catalyst Program, a strategic initiative aimed at consolidating two $1bn commercial businesses. The success of this project has changed the way Nationwide does business by creating a single platform that processes 100% of their commercial policies and enhancing the business experience for over 6000 agents.

In addition, to Nationwide there were 23 other winners each with a unique story of how they had integrated new technology to disturb the status quo within their organizations to improve efficiency or increase profitability. Included in these winners was Chartis, who were acknowledged for their usage of SAS Business Analytics for best practices of improved risk analysis. Chartis has developed a Strategic Risk Analysis (SRA) team. By using SAS this team created a predictive model that identified that fewer than 3% of all companies were responsible for the majority of insurance claims. This predictive model segmented insureds into risk classes having dramatically different loss ratios. Underwriters consulted the model for each submission and focused on increasing market share in the most profitable segments. Within three years, there was 100% growth in the most profitable segment, representing $14 million in new, executive liability business. Read more on the Chartis success story

Finally the event concluded with an interesting panel discussion, including senior executives from Nationwide, John Hancock and Tokio Marine. Continuing the theme of disruption these executives discussed how prepared they are to managing their business real-time. No longer are 5 year business plans acceptable considering how quickly technology is changing. In fact one executive commented when talking about how fast technology changes, that they have given up planning, they are simply learning how to react quicker!

The insurance industry is changing before our eyes, just because you are a successful carrier today does not guarantee success or even survival in the future as demand changes. Think of the transportation industry, the train companies did not become airlines.

I’m Stuart Rose, Global Insurance Marketing Manager at SAS. For further discussions connect with me on LinkedIn and Twitter.

Post a Comment
  • About this blog

    We’re a group of analytics practitioners from the insurance industry. Among us, we have more than 50 years’ experience advising insurance companies across the globe in applying analytics and business intelligence technologies to solve business problems. In this blog, we’ll talk about fraud, risk, regulations, customer value and more, all with an eye toward minimizing losses and maximizing profits.
  • Attending IASA 2012?

    Be sure to attend The Future of Claims:Optimizing Outcomes session

    When: Tues., June 5, 1:30-3:00p.m.
    Where: San Diego
    Featuring: Deb Hammond, Transport Accident Commission; and Stuart Rose, Global Insurance Marketing Director, SAS. Session leader - Jonathan Boylan, FINEOS.

    Connect with me on LinkedIn and Twitter so that we can make arrangements to chat while at IASA.

  • Archives

  • Subscribe to this blog

    Enter your email address:

    Other subscription options