Published on 10 Dec 2012
"We believe that investing in the satisfaction of our customers will yield the biggest long-term payback. " - - Hennie Nortje, Head of Operations, Santam Insurance
BA - Business Analytics, Big Data & Analytics, Big Data & Analytics: Operations/Fraud/Threats, Industry Framework , Smarter Planet
Leadership Series, Smarter Insurance
IBM Business Partner:
Before coming to Santam, Anesh Govender had helped a bank unleash the power of predictive analytics in scoring credit risks. He was determined to apply his insights to streamline Santam’s claims management processes.
Santam didn’t become South Africa’s largest non-life insurance provider by standing still. With rising threats from new classes of competitors in the South African insurance market, Santam’s top management acted to stay on top, kicking off a broad transfor-mation effort with claims processing as one of its key focal points. Taking a cue from the banking industry, Santam saw the opportunity to inject intelligence into the claims management process by modeling the inherent risks of claims based on data generated throughout the process.
Consistent and vocal support from above: The unwavering support voiced by the project’s senior executive sponsor, Head of Operations Hennie Nortje, solidified the mandate for changing the claims process, and laid the groundwork for the broad acceptance of predictive analytics as a power-ful resource. “He’s getting the credit he deserves for supporting me 100 percent throughout the process.” – Anesh Govender, Head of Finance, Reporting and Salvage, Santam Insurance
Allaying the perception that “change equals threat”: Santam found that letting front-line staff in on the benefits of transformation early and often can make allies out of potential detractors. “There was no pushback from the claims employees –who might ordinarily think their jobs are in danger – because we took them along early in the journey.” – Anesh Govender
• Reduced processing time for lowest-risk claims by 90 percent • Saved more than US$2.4 million through early fraud detection and prevention in the first four months • Decreased fraud costs through the repudiation of improper claims • Achieved millions of dollars in cost savings due to improvements in claims processing efficiency • Improved customer satisfaction through faster claims settlement
By the time Anesh Govender was recruited by Santam Insurance to help drive the company’s predictive analytics initiative, its potential to revolutionize the company’s key practices had already taken hold in the minds of Santam’s executives. It had been more than a year since the company’s line-of-business managers had been tasked by the CEO to come up with a new operating model, one that would position the company for the future and help fend off the new and increasingly nimble breed of competitors – including direct insurers – that were making inroads in the South Africa market. Looking across a spectrum of peer insurance companies around the world, the team concluded that the incorporation of predictive analytics into claims processing needed to be a central element of Santam’s broad transformation efforts.
Ironically, when it came to finding an experienced leader who could translate its vision of predictive analytics into reality, South Africa’s largest non-life insurance provider ultimately found that person in an entirely different industry. Before joining Santam as Head of Finance, Reporting and Salvage, Govender was part of a team that helped a major South African bank weave rules-based modeling into credit scoring practices. His hiring reflected a consensus among Santam’s leaders – one that has since been validated by experience – that the key to success in analytics-based projects is in understanding the data, and more importantly, Govender says, “what you can do with it.” Having gained concrete exposure to data management and predictive analytics issues in the banking sector, he was eager to adapt his lessons to the core of Santam’s operations – claims processing.
Applying the lessons of teamwork
Perhaps the most significant lesson he brought along was the need to build consensus on the direction and manner of change from square one. To that end, Govender –who had the enthusiastic support of Santam’s senior management – assembled a multidisciplinary “tiger team” comprised of line-of-business process experts, actuarial and analytics specialists, and key IT staff. As Govender points out, this melding of business and IT was in many ways an outgrowth of what has been a very healthy working relationship between IT and business. “To make that relationship work in this situation, the key was to work together toward a common vision, under a common mandate,” says Govender. “IT wasn’t viewed as an afterthought or a reluctant partner, but an integral part of where we were going.”
Govender and his team were realistic about the challenges of fixing a process whose characteristics – a complex, high-touch flow with multiple decision points, and manual task requirements – seemed to make it almost inherently inefficient. Their aim wasn’t to design a perfect claims process, but to automate and streamline that part of the process where it made most sense. Their beginning point was the assumption that all claims are not the same. Some claims are either large or complex (and therefore risky) enough to require deep human involvement, including the need for on-site inspection by insurance adjusters. Conversely, the majority of smaller or simpler claims don’t justify incurring the cost of traditional processing.
The main thrust of Santam’s plan was to create a new, multi-track processing channel that would accelerate the claims based on their intrinsic risk. As each claim came in, its details would feed into an analytical model that would, in essence, predict whether or not that claim would justify fast-track treatment or should receive the standard– or even higher – level of scrutiny. Govender recognized that the business rules that would underpin this predictive model didn’t need to be invented; they were already embedded in the decades of collective experience held by Santam’s business process experts. The key to his team’s success would be in capturing and structuring that knowledge within a new process.
Planting the seeds of acceptance
Of course, getting that input required the cooperation and buy-in from line employees, not only because of their valuable process knowledge, but also because they would be the group most impacted under the new process regime. Govender will admit that having strong, active sponsorship from Head of Operations Hennie Nortje helped create more receptivity to a new way of doing things. But ultimately, he says: “It was the message itself – that there’s something called predictive analytics and it can help us serve customers better – that had the biggest impact,” Govender explains. “While there was constant reinforcement of that message from our executives, it was the fact that our people were prepared to become educated [about predictive analytics] that lay the groundwork for our success.”
The primary conduit for educating Santam’s employees was an extended series of workshops conducted jointly by Govender’s team and Olrac SPSolutions, a provider of business intelligence solutions (and an IBM Business Partner) that Santam had engaged to design and implement the solution. The purpose of these sessions was to get the word out on what predictive modeling meant to the company as a whole, and for individual employees to get comfortable with it. But just as important, they provided the team with a strong bottom-up understanding of the details of the business, which would prove essential in designing the predictive analytics solution.
On a parallel track, Govender was also focused on evaluating which of Santam’s data sources would be suitable to feed into the predictive model. It was a singularly unglamorous task, requiring many hours of sitting at a screen and looking at flat files. But Govender had done this before, and he recognized that nitty-gritty details like this could have a major bearing on the project’s eventual success or failure. The preliminary steps behind it, the team then set out to implement the solution. Six months later, with the solution entering production, predictive analytics had moved from being an interesting concept to an important element of Santam’s operating model.
Gauging risk to drive the process
From the instant a claim is filed, the bits of information captured by an insurance company – time of day, place, age, auto make and year, to name a few– accumulate fast. By that very point, and in real time, Santam’s solution has already begun assembling these pieces into a mosaic of what it means from a risk perspective. Applying business rules that were distilled from the expertise of Santam’s claims specialists, the solution calculates each claim’s intrinsic risk, and from that, prescribes one of five courses of action, ranging from immediate payment to the triggering of a fraud investigation.
As predicted in Santam’s business case, the solution had an immediate impact on the speed and efficiency of the claims process. Among those claims deemed the lowest risk, the time to resolution was decreased by more than 90 percent. Across claims as a whole, the 70 percent of claims that would ordinarily require as long as five days to settle now take under 48 hours.
Santam Insurance: The parameters of smarter claims management
- Instrumented: From the point of claim submission, the solution automatically extracts key data elements from the claim that represent the building blocks of a risk profile.
- Interconnected: Results from the solution’s risk-scoring engine drive Santam’s claims process workflow.
- Intelligent: By enabling Santam to quantitatively assess claims for their intrinsic risk, predictive risk models provide the company with the means to streamline and optimize the claims process, while improving fraud detection performance.
By the same token, Santam’s ability to safely forego on-site assessments by mobile claims adjusters for lower risk claims has saved millions of dollars in fees and travel costs. But in the big picture, Hennie Nortje, the project’s sponsor and Head of Operations, puts the positive impact on customer satisfaction –by virtue of a far faster payment cycle – at the top of the list of strategic benefits. “By speeding payment, we’ve managed to absolutely delight our customers,” explains Nortje. “We believe that investing in the satisfaction of our customers will yield the biggest long-term payback.”
Uncovering and stopping fraud
While the opportunity to reduce the incidence and cost of fraudulent claims also figured prominently in Santam’s business case, few stakeholders expected a payoff so fast and so large. Indeed, just one month after the solution went live, the analytics engine underlying the claims solution detected the complex patterns that human eyes had not – the existence of major motor insurance fraud syndicate. By foiling that scheme, and detecting and preventing several others, Santam’s claims department saved the company more than US$2.4 million in fraudulent payments in just the first four months after implementation.
Govender points to numerous signs that predictive analytics is percolating into Santam’s day-to-day culture. “It’s been amazing,” says Govender. “The fact that everyone [in claims and IT] is talking about predictive analytics is creating a lot more traction and awareness.” Perhaps even more telling is the way predictive approaches are being applied to a whole new set of claims-related issues, and yielding insights with real business value. For instance, deeper analysis of claims data enabled Santam to create an optimization calculation that determined when it made sense to repair a car and when it didn’t. “Analytics had not been applied like this before,” Govender explains. “It shows how we’re starting to optimize their motor value chain with all the information that the getting out of the system.
Credit where it’s due
Santam’s solution has produced satisfaction among its customers – and has recent customer satisfaction awards to show for it. But its success has also left a favorable mark on employees at every level of the company. Far from pushing back on more predictive processes, front-line claims employees were proud to see their intuitive knowledge embedded in the actual process. As Govender points out, that pride also extends to his boss, the executive responsible for claims “without whose support the project wouldn’t have happened,” says Govender. “He’s getting the credit he deserves for supported me 100 percent throughout the process.”
Santam Insurance’s claims management solution uses...
- IBM SPSS® Decision Management
- Olrac SPSolutions
For more information
Please contact your IBM sales representative or IBM Business Partner.
Visit us at: ibm.com/smarterplanet/insurance
IBM products and services that were used in this case study.
SPSS Decision Management
© Copyright IBM Corporation 2012, IBM Corporation, New Orchard Road, Armonk, NY 10504 Produced in the United States of America. November 2012. IBM, the IBM logo, ibm.com, Let’s Build a Smarter Planet, Smarter Planet, the planet icons and SPSS are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the Web at “Copyright and trademark information” at www. ibm.com/legal/copytrade.shtml. This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided. Please Recycle ODC03222-USEN-00