News & Commentary

11:45 AM
Nathan Golia
Nathan Golia
Connect Directly

3 Ways Insurers Can Win with Predictive Analytics

Implementation of predictive modeling is on a slow but steady climb in insurance. Here's some tips for getting the most out of your initiatives.

Implementation of predictive analytics capabilities has been on a steady rise in the insurance industry. There are implications for all lines of business in terms of how the technology can improve processes. But leveraging predictive modeling effectively means more than just implementing technology. Industry players share these tips for unlocking value from these efforts:

1. Bring in people who understand the readouts

Universal American, the health insurer who spoke to I&T yesterday about beating fraud with predictive analytics, completely remade its SIU in anticipation of the new approach. That didn't mean just bringing in technology folks, according to SIU manager James Cooper. Universal American brought in subject matter experts who could identify potential malfeasance in the data.

"We went from not a very sophisticated SIU to a full-blown unit that has nurses and coders and claims handlers," Cooper says. "Before it was just two handlers that were chasing down claims on a spreadsheet. We went from the stone ages to high tech in the matter of a year."

2. Impart the need for speed to IT

Models have traditionally taken a long time for IT organizations to create and deploy, according to Russ Schreiber, insurance industry principal for FICO, which partnered with Universal American on its predictive modeling initiative.

"The first challenge that we've seen is that a lot of carriers have all sorts of models, but they can't get them into a decision stream," Schreiber says. "The tech is solved, but the challenge is as much around culture. Once it's done, you shouldn't have to wait a year for it."

The velocity of "big data" demands a quicker turnaround as well, Schreiber adds.

"There's an awareness at the organizations that they've got this data and this knowledge," he explains. "And, it's much more readily available. It's much less this IT extraction initiative to get this data to the modeling teams. So people know they can get the data."

[See also: CIGNA's Mark Boxer opines on the potential for big data in insurance]

3. Don't discount public data

Towers Watson's recently released predictive modeling benchmarking study revealed that smaller insurers "face growing competitive pressure from large, resource-rich insurers" due to a perceived lack of data resources. But the consultancy says there are ways that companies of that size can "fast follow," including access to competitor filing materials.

FICO's Schreiber goes a step further, saying that no data set is complete without data from outside the organization.

"The ability to access the data has moved so far so fast, and it's internal as well as external sources," he says.

Nathan Golia is senior editor of Insurance & Technology. He joined the publication in 2010 as associate editor and covers all aspects of the nexus between insurance and information technology, including mobility, distribution, core systems, customer interaction, and risk ... View Full Bio

Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
Tony Kontzer
Tony Kontzer,
User Rank: Apprentice
2/7/2013 | 8:06:04 AM
re: 3 Ways Insurers Can Win with Predictive Analytics
I think that points 1 and 3 here are especially applicable across industries when it comes to deriving value from predictive analytics. Without subject matter experts who know what to glean from the data, there is now way realize the full potential of any efforts at predictive modeling. And with most companies now realizing that making decisions based on their own relatively puny and limited data sets is to leave the universe of available data on the sidelines, public data sources clearly must play an ever-growing role.

Tony Kontzer
InformationWeek Contributor
Nathan Golia
Nathan Golia,
User Rank: Author
2/4/2013 | 3:42:19 PM
re: 3 Ways Insurers Can Win with Predictive Analytics
Good point, Murali. I just finished a call with an insurer executive talking about analytics and one of the points that stood out to me was that analytic insights must be credible and unbiased to get buy-in from the entire enterprise.
User Rank: Apprentice
2/4/2013 | 7:34:18 AM
re: 3 Ways Insurers Can Win with Predictive Analytics
As long as biz-sees true value from-predictive analytics(PA) from the biz context, demand for PA-will grow.Both IT and Biz will have to work very closely in order to-stay in the game well ahead of the competitors and gain more wallet share.
User Rank: Apprentice
2/1/2013 | 9:27:37 PM
re: 3 Ways Insurers Can Win with Predictive Analytics
FICO and their predictive analytics for medication compliance is the biggest rip around wiht trying to turn linear data into non linear relationships.- It is so obvious that the average consumer sees it and the problem is- querying credible and not credible data and they don't even give the sources out.- If you have not watched the documentary, Quants, the Alchemists of Wall Street then you will understand how the models get built wiht a bit of fiction and some old time quants have some great advice.- Mike Orsinki, who built the mortgage software that all used in the scam has a great line in there, "you can do anything with software"...but it is good and relative.- You have been Algo Duped with formulas created only for making money negligent of accuracy and ethics.- I keep that video visible on every page of my blog to help educate consumers and there's 4 others on there that are good too to include a former quant who worked at DE Shaw. I used to program and I know crappy and mis matched data when I see it with no value.- I told that to a journalist at Proto magazine years ago from UMASS and we are in the thick of it now.-

Here's my opinion on FICO and the medication behavior's a rip and a lot of fiction and huge marketing efforts to try to convince phara and insurance companies it has value.- They are bad enough on their own and I would think they have enough sense not to bite on this themselves...they just got into revenue the news about all the flawed software to show more frequently..just as I said it would 3 years ago.

Here's my in depth opinion of the FCIO medication scam of matching data that is not relational.
User Rank: Apprentice
2/1/2013 | 12:18:17 AM
re: 3 Ways Insurers Can Win with Predictive Analytics
"We went from the stone ages to high tech in the matter of a year." This statement is probably fairly representative of how the "shoe leather" school of fraud investigation has finally seen the value of taking full advantage of the technological side of fraud detection.-
User Rank: Author
1/31/2013 | 9:19:33 PM
re: 3 Ways Insurers Can Win with Predictive Analytics
Regarding #2/Need for Speed -- do you think this is why we're starting to hear about "big data in the cloud" -- that is, it's not just changing the IT org's orientation/processes to do these things more rapidly; it requires an infrastructure that enables speed, responsiveness, flexibility, "just in time"
Register for Dark Reading Newsletters
White Papers
Cartoon Contest
Write a Caption, Win a Starbucks Card! Click Here
Latest Comment: This is a secure windows pc.
Current Issue
Security Operations and IT Operations: Finding the Path to Collaboration
A wide gulf has emerged between SOC and NOC teams that's keeping both of them from assuring the confidentiality, integrity, and availability of IT systems. Here's how experts think it should be bridged.
Flash Poll
New Best Practices for Secure App Development
New Best Practices for Secure App Development
The transition from DevOps to SecDevOps is combining with the move toward cloud computing to create new challenges - and new opportunities - for the information security team. Download this report, to learn about the new best practices for secure application development.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
Published: 2017-05-09
NScript in mpengine in Microsoft Malware Protection Engine with Engine Version before 1.1.13704.0, as used in Windows Defender and other products, allows remote attackers to execute arbitrary code or cause a denial of service (type confusion and application crash) via crafted JavaScript code within ...

Published: 2017-05-08
unixsocket.c in lxterminal through 0.3.0 insecurely uses /tmp for a socket file, allowing a local user to cause a denial of service (preventing terminal launch), or possibly have other impact (bypassing terminal access control).

Published: 2017-05-08
A privilege escalation vulnerability in Brocade Fibre Channel SAN products running Brocade Fabric OS (FOS) releases earlier than v7.4.1d and v8.0.1b could allow an authenticated attacker to elevate the privileges of user accounts accessing the system via command line interface. With affected version...

Published: 2017-05-08
Improper checks for unusual or exceptional conditions in Brocade NetIron 05.8.00 and later releases up to and including 06.1.00, when the Management Module is continuously scanned on port 22, may allow attackers to cause a denial of service (crash and reload) of the management module.

Published: 2017-05-08
Nextcloud Server before 11.0.3 is vulnerable to an inadequate escaping leading to a XSS vulnerability in the search module. To be exploitable a user has to write or paste malicious content into the search dialogue.

Dark Reading Radio
Archived Dark Reading Radio
In past years, security researchers have discovered ways to hack cars, medical devices, automated teller machines, and many other targets. Dark Reading Executive Editor Kelly Jackson Higgins hosts researcher Samy Kamkar and Levi Gundert, vice president of threat intelligence at Recorded Future, to discuss some of 2016's most unusual and creative hacks by white hats, and what these new vulnerabilities might mean for the coming year.