The business case for reducing fraud is compelling for property and casualty insurers. With fraud on the rise and accounting for an increasing number of claims, reducing its incidence by as little as one or two percentage points can push millions of dollars to a carrier's bottom line. An estimated 10 percent of all U.S. P&C claims are fraudulent, and we estimate that fewer than 20 percent of those are detected or denied.

Predictive analytics can be a powerful weapon in the battle against fraud. By modeling past incidences of fraud, and pairing those results with social-network analysis, predictive analytics can help insurers understand what it is about a claim, claimant or insured party that correlates with a higher propensity for fraudulent behavior. Predictive analytics can help insurers discover sophisticated fraud rings and help them intervene earlier in the claims process to prevent payment for a fraudulent claim.

Predictive analytics is the process of analyzing historic and current data and generating a statistical model to help predict future outcomes. At the heart of this approach is the concept of predictors: one or more variable factors likely to influence an outcome that can be measured or scored to predict probable results.

Predictive analytics improves the claims process in several ways. It can dramatically strengthen customer relationships by helping insurers understand customers and, subsequently, meet or exceed their expectations. Key to doing so is reducing complexity and cycle time for legitimate claims.

Poor customer service is closely tied to the incidence of fraud against P&C insurers. Results from the Accenture Insurance Consumer Fraud Survey 2010 found that poor service actually encourages fraud, with 55 percent of survey participants saying that poor service from an insurance company might make an individual more likely to commit fraud against that company.

But the benefits of predictive analytics are not limited to customer-facing situations. Predictive analytics can improve the overall claims process by enabling claims leaders and employees to become more engaged, inspired and confident. For example, analytics can help an insurer's claims professionals focus on the activities that make the most difference for the insurer from a business perspective. In other words, predictive analytics can give claims professionals insights into the complexity and severity of claims, as well as into all the elements they need to understand how to manage a claim most effectively—rather than forcing them to guess and cobble together pieces of information to develop their strategy.

With fewer qualified people to work on claims and insufficient supporting tools, insurers' claims departments are increasingly burdened. Our own research indicates that claims personnel at major insurers spend at least half their time on administrative tasks and have difficulty managing loss costs due to such things as fraud. In an environment where claims professionals already have trouble focusing on value-added activities and on delivering consistent outcomes, carriers face the added challenge of higher levels of fraud.

Predictive analytics can improve the employee experience by ensuring the right people are working at the right time to get the right outcome—for instance, having an expert available to study a particular part of a claim.

These capabilities, however, cannot be bought "off the rack." Insurers looking to make predictive analytics a core part of their claims operations need several key capabilities. In our experience, there are two tiers of required capabilities: those necessary to establish a basic predictive-analytics process, and additional assets and skills needed to translate insights generated into lasting competitive advantage.

One of the key requirements for getting started is effective data-quality assessment and preparation. In brief, insurers must understand which business problems they seek to solve with predictive analytics, and then ensure that they have a sufficient supply of high-quality data related to those challenges and their respective business functions or processes.

Once an insurer has determined it does have enough high-quality data to work with, it must develop or obtain access to the analytical capabilities required to construct accurate predictive models.

Systems integration also plays a major role, as insurers will need to link their predictive analytics tools with other key enterprise systems so they can conduct real-time analytics. Insurers also must build an appropriate operating model (including organization, processes, talent and metrics) that enables them to institutionalize their predictive analytics approach throughout the business, as well as a technical architecture that provides an appropriate platform for hosting their analytics tools. Of course, robust program management is crucial to supporting the development and rollout of these capabilities to foster their adoption across the organization.

Ultimately, predictive analytics can increase an insurer's financial stability. By using predictive analytics to improve customer perceptions and the employee experience, an insurer can realize significant business benefits in the form of a reduction in losses due to undetected fraud, improved precision in loss reserving and greater efficiency through superior unit-cost management. In a business environment that is only beginning to turn around for insurers, that should be ample motivation for exploring this powerful and innovative technology.