The business of insurance is constantly changing and evolving.As society grows and trends in differing directions, so too mustthe insurance industry read and react to what goes on around it.The industry can be a step behind if it is unable to quickly reactor digest enterprise data. This delay is a vulnerability which canbe exploited in the wrong hands, leaving the door open tofraud.

|

Data is one of an organization's most valuable resources, asCEOs, CIOs and CFOs are rapidly learning. According to recentindustry studies, insurance carriers are implementing more complextechnology and analytics at a faster pace than ever before. Thisincreasing investment in technology is part of an overall insuranceindustry investment trend to leverage "big data" resources. Havingthese capabilities has fast become a top organizational prioritybecause of how data analytics drive improvement opportunities toall aspects of business operations.

|

Given this environment, it's no wonder that data analytics hasbroken through to the mainstream so quickly. However, data is a"raw" resource and needs to be drilled, mined and processed into auseable commodity for its consumers.

|

Based on the nature of fraud and the speed at which it canoccur, having proactive capabilities in place is an essentialstrategy. There are a variety of tools and solutions offering userinterfaces and information that is easy to consume, thus improvingthe various processes for detecting fraud or claims exaggeration byobjectively comparing facts and scenarios without prejudice orbias.

|

While no one can forecast the future, successful claim modelsare precipitated by calculated processes and collaborativeteamwork. Simply stated, the more one has access to and understandsdata, the more one can be better prepared for what lies ahead.

|

Building an SIU protocol

|

The key to building a better SIU (special investigative unit)protocol is acquiring an effective technological platform ofsolutions and tools. Foundationally, a successful platform is builton harvesting data from a number of internal and external sources.Accessing and aggregating multiple disparate data sets into adigestible format allows SIU operations to develop more effectivestrategies that can speed fraud detection, identify new insightsand predict emerging exposure trends.

|

Critical data types for fraud modeling include policy andapplication details; structured and unstructured claims data;investigative results; vendor data; industry watch list data; andthird-party data. Most carriers invest significant resources invendor and third-party data. An ability to leverage these raw dataresources results in a much more holistic, robust view of the"internal universe." Adding sources such as ISO loss history, watchlists, public records, medical billing data, underwritinginformation and auto estimates can have tremendous impact on fraudmodeling.

|

The challenge is that all of this data is often located indisparate, walled-off servers generally maintained by a number ofdifferent departments such as claims, underwriting, sales, IT andfinance. Further, the data is usually in varying formats. How doyou get "one version of the truth" for the data? Technology iscritical to extracting, transforming and loading the data acrossthis infrastructure so that advanced analytical processes can beapplied. Data management technology and processes must be able tocleanse and enrich data, conduct entity resolution for multiplevariations of the same data and improve overall quality. No matterhow advanced the analytics are, results will be limited if the datamanagement process is not robust. As the saying goes, "garbage in,garbage out."

|

Determining data sets

|

Once the critical step of aggregating data happens, the data setcan be utilized by an integrated fraud detection solutions andtools platform. For investigative teams, most fraud solutions allowfor automation of the fraud detection process. Multiple modelingtechniques and different analytical approaches are embedded. Thisincludes techniques such as anomaly detection, predictive modeling,link analysis, text mining and automated business rules. Theseanalytics can be layered into decision-making engines that processa steady stream of data 24 hours a day, seven days a week.

|

There are common triggers or events that exist within acarrier's files spread across a universe of claims. The challengeis how to better identify these scenarios early enough toeffectively manage the inventory. One method is for all claims tobe scored and ranked in terms of fraud propensity based on valuesderived through complex algorithms and advanced mathematicaltechniques. These should be applied to the data associated witheach claim while also assessing relativity to the entire claimpopulation.

|

With technology, claim fact outliers, questionable links andsuspicious loss indicators can be identified within the data at aconsistent power and speed not achievable through traditionalmanual detection processes. In addition to highlighting specificreasons why a claim is high-scoring, a user interface can aggregatedata details that support the reasons identified through theanalytic detection process. From a business perspective, thisallows limited SIU resources to efficiently and effectively focuson the most egregious fraud risks. Legally, this detection approachprovides significant bad faith risk mitigation through automatingscientifically and mathematically-based analytical methods on aconsistent basis.

|

|

Utilizing the information

|

The use of data analytics tools and the role of the datafunction are expanding, thereby allowing SIU to become moreoperationally sophisticated. Consequently, most carriers understandthe importance of harvesting internal data for investigations andhave created analyst positions within claims or SIU. These analystsare tasked with identifying emerging trends at the enterpriselevel.

|

Generally, they are focused on a strategic "top down" approachto identify the proverbial "needle in the haystack." Tools allowanalysts to drill into and create new views from the universe ofclaims data, including the analytic output from fraud solutions.Based on discoveries derived through leveraging tools, analysts cancreate and test new fraud scenarios against enterprise data. Thishelps to identify emerging anomalies linked to billing trends andnew schemes potentially impacting lines of business for specificgeographies or the enterprise.

|

A further benefit to data analysis is that claims leadership canbe informed in order to develop strategies, make resource decisionsand more effectively collaborate throughout various departmentswithin the organization. This goes well beyond fraud to includevarious business challenges such as identifying medical managementand subrogation claims, determining litigation propensity andmanaging the life of a policy. No matter what the intended purpose,the end game of advanced data analytics is to focus the entirety ofa claim environment into a single space.

|

Taking fraud detection to the next level

|

How can an organization best operationalize a fraud detectionplatform? The notion of such a concept may seem daunting. Itrequires leadership and change management skills to execute asuccessful enterprise adoption strategy. Planning needs to occur assoon as technology is acquired and consideration has to be given onhow to roll out a solution across an organization. First andforemost, the end user of the platform must understand the conceptthat data and analytics enhance the ability to apply their subjectmatter expertise and quickly gain valuable insights for focusedinvestigative leads.

|

The messaging of this benefit must be clearly communicatedthroughout an organization. Most importantly, SIU personnel must beengaged in the vetting of a fraud solution and implementationprocess. This is critical for ultimate ownership and adoption.Effectively employing a solution into operations and subsequentlyevolving it may call for an iterative approach. An organizationneeds a starting point to begin the analytic journey.

|

Significant metrics can be derived from a platform. Analyticsalso allow understanding of how effective investigative efforts maybe and where opportunities for improvement may exist. Operationaldashboards and analytics can be developed to provide deeperinsights into core SIU pillars such as processes, functions andstructure to improve strategy. An effective knowledge managementsystem is certainly a core process to capture institutionalknowledge. Results from previous investigative efforts are criticalfor predictive modeling to improve fraud detection models. Thisrepresents a real return on investment in analytics.

|

In short, the integration of data analytics into the insuranceindustry is here. There is no doubt that technological solutionsand analytics can significantly enhance SIU capabilities andeffectiveness. With the growing power of fraud platforms toleverage "big data" and apply advanced analytics, new andcomprehensive understanding of enterprise fraud risk ispossible.

|

Technological advancements have created user-friendly platformsand provide a tool to assist leaders, analysts and investigators infocusing their expertise on critical issues. Attorneys can useinsight from analytics to pursue affirmative litigation actions andas a shield to mitigate bad faith risks.

|

Analytics is not a replacement for the investigator or adjuster.Instead, it enhances the position to promote efficiency in theclaim environment. The key is in understanding and embracing thepower of technology and analytics when combined with insurancedata.

|

James Hulett is a security and intelligence businessconsultant at SAS where he consults on implementing and integratinganalytic solutions into insurance operations to solve businesschallenges. He is a former assistant vice president of the SpecialInvestigation Unit at The Hartford and may be reached at[email protected].

|

Jeffrey G. Rapattoni co-chairs the Fraud/SpecialInvestigation Practice Group at civil defense litigation firm,Marshall Dennehey Warner Coleman & Goggin. He may be reachedat [email protected]

Want to continue reading?
Become a Free PropertyCasualty360 Digital Reader

  • All PropertyCasualty360.com news coverage, best practices, and in-depth analysis.
  • Educational webcasts, resources from industry leaders, and informative newsletters.
  • Other award-winning websites including BenefitsPRO.com and ThinkAdvisor.com.
NOT FOR REPRINT

© 2024 ALM Global, LLC, All Rights Reserved. Request academic re-use from www.copyright.com. All other uses, submit a request to [email protected]. For more information visit Asset & Logo Licensing.