If insurers could somehow forecast the future, what a safer,more productive, and more profitable future it might become. Lossprevention departments could greatly reduce both claim frequencyand severity, while growth could be focused to mitigate catastropherisk.

While we await a crystal ball, all kinds and sizes of losses aretaking place. The good news is that tools are now available to helpshine a light on important issues within the insurance industry.Big data and predictive analytics have held a firm foothold inunderwriting and actuarial departments for years, and many arefinding they also have a place in handling Workers’ Compensationclaims. As models are refined, more insurers are learning how toimprove outcomes and their bottom line.

The key to successfully incorporating a predictive model is totarget opportunities where data can give a claims organization thebiggest lift, with the lowest-hanging fruit clearly being claimseverity. At the National Council on Compensation Insurance 2015Annual Issues Symposium, 32 states reported an increase in averageannual Workers’ Compensation claim severity between 2009 and 2013,and this is a trend that deserves attention. From claim assignmentthrough settlement, identifying claim severity early and accuratelycan help put claims departments in the driver’s seat, allowing aproactive and informed approach to claims handling.

Photo: baranq/Shutterstock

When claims spiral out of control

Even the most seasoned adjusters occasionally find that claimscan spiral out of control. This can happen for a number of reasons:heavy caseloads, frequent file transfers, lack of information andinexperience in spotting the severity indicators of a particularclaim. Assigning the right claim to the right adjuster is only halfthe battle. The adjuster must have the experience and skillnecessary to identify severity indicators early on in the life ofthe claim.

The adjuster must also devise an appropriate plan to bring theclaim to resolution and get the injured claimant to maximum medicalrecovery and then back to work, if possible. No matter how deeptheir experience, adjusters will likely encounter claims withunfamiliar characteristics. For a newer adjuster, this can bedaunting. Controlling costs becomes even more difficult when claimsare reassigned and each successive adjuster must make a seamlesstransition in identifying the proper steps to take in handling theclaim. With each reassignment, the likelihood of potentially severeclaims falling through the cracks — resulting in skyrocketing costs— increases exponentially.

Using data and analytics to improveoutcomes

Spotting high-risk claims early in their lifecycle can be key tomitigating costs and improving outcomes for all parties involved.With the increasing availability of big data, it has never beeneasier to incorporate predictive modeling into the claims process.This changes the process from relying on the experience of a singleadjuster to drawing on the claims experience at the company level,which may mean hundreds of thousands of claims — or even to theindustry level, which may involve millions of claims.

The challenge of correctly identifying many potentially severeclaims early-on can confound even the most seasoned adjusters. Datasupplied by a solid predictive model can accelerate experientiallearning and provide a safety net for adjusters by providingdata-driven indicators to flag claims that may spiral out ofcontrol without proper attention. Pairing severity identificationwith business process can yield even greater results.

Given a predictive model providing a range of severity scores,for example, it makes sense to assign the least severe claims tonewer adjusters, providing them with low-risk claims so they canlearn the fundamentals of claims handling. As experience levelsrise, so should the complexity of claims assigned. This allowsadjusters to deepen their experience level while optimizing claimoutcomes for claimants, employers and insurers.

Beyond triaging claim assignments, severity thresholds can bebuilt into the claims handling process. For example, autoadjudication may be incorporated for the lowest-severity claims,while actions such as mandating nurse case management and increasedmanagerial oversight may be considered for the highest-potentialclaims. This allows a claims department to focus its time, energyand expenses where they can have the greatest impact onhigh-severity claims.

Photo: GustavoFrazao/Shutterstock

Why predictive analytics?

With the unprecedented availability of data, it has never beeneasier to reap the benefits of establishing a claims processinformed by predictive analytics. Incorporating a robust model canyield a valid statistical basis for decision making, which stronglyaugments the decision-making ability of claims staff. When decidingif this is the right time for employing analytics, it is importantto consider not only potential return on investment, but also thevery real cost of inaction. Claims severity continues to rise,driven by medical and indemnity costs, for which the NationalCouncil on Compensation Insurance reports a cumulative increase of226.7% and 135.2%over the past 20 years, respectively.

Adjuster experience, while invaluable, is not infallible. A goodpredictive model informs, but does not replace claims experience indecision making. It helps adjusters and management focus attentionwhere it is most needed, minimizing the risk of exploding claimsand reigning in unnecessary expenses with potential for directlyimproving an insurer’s financial results.

The human element will continue to impact the claims process —just as it should, given the insurer’s goal of helping claimantsdeal with unexpected losses that may represent life-changingcatastrophes. But the development of finely tuned analytical modelsis yielding insights into those claims to bring a sharperunderstanding of their potential severity and helping inform thoseinvolved in the claims process from assignment to settlement.Although not yet a crystal ball, better analytics are opening newwindows and providing a clearer view into the world of claims.

Adam Wesson is the director of claims solutions for ISOClaims Partners, a Verisk Analytics (Nasdaq:VRSK)business.