Claims Analytics: Using Predictive Analytics to Optimize Your Claims Processes

By Stuart Rose

There are no easy ways to grow revenue, increase profit or improve market share in the insurance industry right now. Increasingly, insurers need to look internally to trim expenses and improve business processes to keep shareholders happy. One way to do this is to employ predictive claims analytics to optimize loss reserves, increase productivity and assist in preventing fraud.

An insurance company’s claims are a rich source of data that go mostly untapped because more than three-quarters of the data is unstructured. Adjuster notes, medical records and police reports can provide invaluable information – if that information can be viewed in context. Take fraud, for example. An adjuster will not necessarily know that his assigned case involves a medical specialist who bills for a large number of treatments as compared to another medical specialist billing for similar injuries. But if the insurer can analyze the text embedded in medical claims, the possibility of fraud becomes evident and can be the basis of an investigation.

However, claims analytics go beyond fighting fraud and identifying outliers. It can enhance the bottom line by:

• Helping adjust loss reserve funds by providing up-to-the-minute information. Imagine if your organization knew on a daily basis how much to set aside for losses. If a claim could immediately be scored for probable cost (e.g., accidents with bodily injuries graded higher than fender benders), your organization could adjust reserves just as quickly. Even comparatively small differences could be analyzed (e.g., the probable cost of a claim where a motorist hits a tree going 20 mph vs. 40 mph) – and factored into loss reserves.
• Reducing settlement lags and claims payout. Predictive analytics has 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. For example, the size of a claim can increase by approximately 50 percent if the insured does not report the claim within the first four days.
• Automatically assigning adjusters according to priority and skill set. When a claim is initially reported (either via the Internet, telephone or fax), the claim is often assigned to an adjuster based on the limited information available in the First Notice of Loss. By using predictive modeling techniques based on the loss characteristics (such as loss type, location and time of loss, etc.), claims can be scored, prioritized and assigned to the most appropriate adjuster.
• Analyzing claim data to help with subrogation. Insurers often only receive a fraction of not-at fault settlement costs because they don’t pursue subrogation opportunities. Claims analytics help insurance companies find these opportunities by identifying known subrogation characteristics and optimizing associated activities; therefore, loss adjustment expenses are lowered.
• Reviewing claims for possible litigation. 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 adjust loss reserves accordingly.
• Optimizing the limits for fast-track claim settlements. Research has proven that a positive claim experience improves customer satisfaction and subsequently increases policy retention. Hence, insurers have implemented fast-track settlement and mobile claims processes that settle claims instantly. But writing a check on the spot can be costly if the insurer overpays. Any insurance company that has seen a rash of home improvements in an area hit by a natural disaster knows how that works. By analyzing claims and claim histories, companies can optimize the limits for instant payouts.
• Fighting increasingly sophisticated fraud. Claims analytics doesn’t just find suspect providers; it can unearth rings of fraudsters by analyzing data for social networks. Have you been hit by several claims from different people who all happen to be using the same address? Or have several suspect claims used the same body shop? Without using network-link analysis, you can’t discover these associations.

Many solution providers allege to offer claims analytics for insurers. But, what most vendors really offer is simple business-rules software that red-flags problematic claims (e.g., the stereotypical 19-year-old in an accident with a two-day-old sports car). Other solution providers focus on workflow optimization, essentially as a means to digitize all of the paper files spilling from adjusters’ desks. Digital solutions and business-rules applications are important components, but they don’t replace predictive analytics.

Predictive analytics integrate with your claims management solutions, analyze your data and make business rules more effective. For activities such as recalculating loss reserves daily; providing sophisticated approaches to fraud reduction; helping assign the right adjuster; and flagging and routing possible salvage and subrogation claims, predictive analytics let your company increase profit by being more efficient.