Friday, May 11, 2018

Why do auto Insurers experience so much fraud at point of sale?

The auto insurance industry has a fraud problem at the point of sale. Industry studies and our own work with carriers indicate that this type of fraud constitutes upwards of 10% of net premiums. Yet by and large carriers don't focus much resource on fighting up-front fraud. I think it's in part because historically they have been too pessimistic about achieving results. Specifically in the past they've assumed:

"There's not enough time" - The modern auto insurance quotation and purchase process is designed to be completed in a matter of minutes, therefore there is no time for the carrier to examine the customer's data and investigate questionable details. If they try, the customer will go someplace else.

"There's no ROI" - The dollar value of each instance of point of sale fraud is small, running from $50 to about $1,000 per policy. It costs more in underwriter investigation time than the potential savings.

"There's too much uncertainty"  - Carriers use third party data to test the validity of various key rating factors like territory, drivers, vehicles and so on but this data is only 80-90% accurate. Carriers don't want to reject good business based upon bad data so they're reluctant to 'pull the trigger' even when the data tells them they should.

But these assumptions are rapidly becoming obsolete and are leading carriers to ignore a significant profit and pricing opportunity.

"There's not enough time" is no longer true because new tools are available that automate the identification and measurement of fraud risks within a quote session's short duration. 

"There's no ROI" is becoming obsolete because these same tools are increasingly able tyo automate the process of challenging data claims and collecting documentary proof at POS, eliminating almost all of the burden historically borne by Underwriting.

Finally,  "There's too much uncertainty" is only true because carriers mistakenly focus on the data rather than the customer. The data is simply a 'tip and lead' that indicates that there might be a problem. Only the customer can tell the carrier whether the tip is true. And they usually do because once a fraudster thinks a carrier has found him out, he typically abandons the quote and goes elsewhere. Customers who aren't trying to defraud - the 'false positives' - won't run away just because the carrier asks them a question. This means carriers don't need perfect data - the combination of "good enough" data and new rapid customer interaction tools provide far more insight.

The bottom line is that if carriers update their assumptions about the feasibility of fighting POS fraud they'll find a large and very accessible profit and pricing opportunity. How do I know? Because we're already doing it for their competitors.

Thursday, October 6, 2016

How to solve the Commercial Vehicle Classification as Personal Vehicle Problem

It turns out that quite a few owners of commercial vehicles dishonestly insure them as personal vehicles.  Indeed in our personal automotive insurance policy database of millions of customers, roughly 1 percent of all vehicles are actually commercial. And it's not hard to understand why  - it's a lot cheaper. Commercial auto insurance is more expensive because it carries:

  • Higher Liability Minimums: Depending upon usage, commercial vehicles are often required to carry higher liability insurance limits. For example in California a personal minivan seating 7 is required to carry $15,000 per individual /$30,000 per accident/ and $5,000 property damage coverage or roughly $50,000 in total while an equivalent commercial van carrying passengers is required to carry a minimum of $750,000 in general liability coverage.
  • Higher Risk:  Commercial vehicles often have many potential drivers, who cannot be evaluated for their driving history.  Commercial policies are also broader - for example they often cover damages from pickup and delivery. And commercial vehicles are used for a wide range of different activities - some of them quite dangerous. All these higher risks lead to higher rates.
  • Higher per vehicle value: Commercial vehicles often have expensive features that personal vehicles don't , like heavy duty suspensions or customized additions to carry and store equipment.  So the replacement value is higher leading to higher rates.

These factors result in premiums that can be multiples of an equivalent vehicle on a personal auto policy. So it's understandable that some customers would try to game the system. Unfortunately it's often quite difficult to identify a vehicle with a Commercial Vehicle Misclassification Problem until a claim comes in.  And sometimes not even then.  This is because:

  • Many commercial vehicles are the same makes and models as those commonly used as personal vehicles so Vehicle Identification Numbers are not a useful guide to identify them.
  • Nor is Commercial registration a reliable guide to commercial use because to save money, policy holders often register commercial vehicles as personal ones.
  • The total value to be covered often will exclude expensive commercial modifications that were acquired in the after market and not reflected on vehicle purchase records.

Needless to say, the Commercial Vehicles Misclassification Problem is a significant source of premium leakage. Assume conservatively that these misclassified vehicles would carry a commercial premium twice that of a personal policy. If the data are right and 1% of all insured vehicles in a portfolio are misclassified, then the premium leakage for this type of misclassification alone could equal or exceed 1% of revenue.  If that's the case then eliminating even a fraction of these data defects could have a significant impact.

VeracityID can help insurers crack this problem. idFusion gives insurers tools like idAnalyze (TM) which allows them to create business rule sets that serve as risk indicators for the presence of a commercial vehicle.  idFusion then enables insurers to automatically intervene within the customer or agent's application session and gather additional information or documents such as a photograph of the vehicle to validate the customer's claim. Indeed, idFusion delivers the alerts, workflow and tools that enable insurers to identify, address, intervene and ultimately prevent these events from occurring.

The good news is that the Commercial Vehicles Misclassification Problem has a solution that idFusion can deliver for insurers. The bad news is that if they don't choose to implement then it's the honest policy holders that foot the bill. We think that's wrong - which why we founded VeracityID.

Thursday, August 4, 2016

How to get your auto insurance company to fix your car for free

Say you have some damage to your car:  nothing big, maybe a few dents up front with some scratches amounting to a couple thousand dollars in repairs.  Here's how to get an insurance company to pay for them. For free:

Step 1 - Sign up for an expensive Comprehensive and Collision policy with a low deductible - don't worry about the expense - the goal here is to get the best coverage possible. Get immediate coverage and ask them to bill you.
Step 2 - Immediately file a claim for the damage you want repaired.
Step 3 - Within a few days the claim will be paid.
Step 4 - Once you have the money in hand cancel the policy, just throw the premium notice away.

Is this honest? No. Does it happen? Sadly, all the time. For three reasons:

Some consumers cheat. Using VeracityID's database of millions of policies we've found that customers who establish new Comprehensive and Collision policies submit claims at a two to four times higher rate in the first month than in the other 11 months of their coverage period. Clearly some customers are 'saving up' their claims for when they get 'better' insurance. And insurance companies encourage this behavior by in most cases letting them.

Insurance information systems are antiquated and fragmented.  It is quite likely that your insurance company - or one you can find  - has no real time integration between its billing and claims paying systems. Typically they'll note the enrollment event but often only update premium payment status periodically.

Regulations enable it. And since most jurisdictions require claims to be paid far sooner than the time in which a premium bill becomes past due, a dishonest customer can game the gap caused by weak insurer technology.

Insurers struggle to prevent this because to do so they need to have indications as to which claims are for preexisting damage. But since we estimate that 97 percent of US consumer auto policies are written without a physical inspection insurers end up paying all of the claims. So long as the claim size is modest <$5,000 insurers likely won't scrutinize the claim. And even if the customer can't get it fixed for free, he can still get thousands of dollars damage for the price of a single month's payment plan premium. Thousands of customers do this every day, rocking back and forth between Minimum State Liability insurance and Comprehensive and Collision insurance as their car damage dictates.

The First Month Excess Claims Problem is an example of how idFusion(TM) can be used to discover and measure the magnitude of hidden fraud. idFusion gives insurers tools like Policy Time Migration (TM) which arrays all customer policies by Policy Year. Using this, carriers are able to identify and analyze event "hot spots" across the Policy Life Cycle by time and policy element. Hot spots like the First Month Excess Claims Problem. Once problems are identified, idFusion delivers the alerts, workflow and tools that enable insurers to address and ultimately prevent these events from occurring.

The good news is that the First Month Excess Claims Problem has a solution that idFusion can implement for insurers. The bad news is that if they don't implement it then it's the honest policy holders that foot the bill. We think that's wrong - which why we founded VeracityID.

Friday, April 22, 2016

Breaking the Logjam in Auto Insurance IT

Online, real time pricing and the “20% fraud” problem in Auto Insurance
Customers have been taught by the increased adoption of the internet for financial services to expect real time quoting and approval of financial products. But P&C Insurers lack the infrastructure to deliver instantaneous decisions that accurately reflect the true policy risk. So carriers have responded to the demand for instantaneous action by relying on agents and/or adapting legacy systems to the real time tempo using "Chewing gum and baling wire". But since an estimated 20% of auto premiums were already fraud and underwriting ‘leakage’, the risk of fraud is bound to rise. So carriers are racing to replace existing systems with new technology that can better support real time operations.

The IT Logjam
This has led to a massive logjam of core systems projects to deliver such laudable goals as “straight through processing”, “customer intimacy” and “lower transactions cost”. However, if you isolate the critical drivers of success, the core challenge is, as always: “price the risk right” with the added requirement of “do it right now”. Indeed, the two core challenges of any P&C insurer are right pricing the risk and paying only valid claims. Everything else, from policy administration, to billing, to CRM are important supporting capabilities but none of them drive the core economics of the business the way that risk pricing and claims decisions do.

Making the Right Decision, Right Now
So we asked the question: What would it take to enable carriers to focus directly on (1) Making better risk/pricing decisions and (2) Identifying customers at a high risk of claims fraud up front and continuously thereafter? idFusion was the result. In conjunction with a Top 5 Global Insurer we developed a solution that:

Delivers a valid risk/claims/profile of each customer
  • Directly accesses existing customer information in legacy systems
  • Fuses it with readily available external customer information 
  • Identifies excess claims 'hot spots' for further analysis and resolution
Screens customers in real time
  • IDs data errors and fraud to price the real risk
  • Flags applicants and customers at high risk of claims fraud 
  • Screens continuously for changes thereafter
Delivers results far faster, bypassing the Core Systems “logjam”
  • Not a system of record and therefore poses little execution risk
  • In 'The Cloud' with minimal impact on carrier infrastructure or IT resources
  • Deployed in months rather than years using existing data sources
  • Deployed as a service that can be turned on or off 
  • At a cost that is a small fraction of Core Systems implementation
Delivers 3 to 5 percent of premium savings within 18 months and offers an opportunity for much more thereafter by directly targeting the sources of mispricing.

It's created quite a stir at our lead customer, they're saying things like "we've never been able to see our data like this before" and "up until now it's been locked up in old systems".  If you're in the P&C Insurance space you should check us out.

Tuesday, March 8, 2016

The only thing worse than growing too fast is growing too slow

The Property and Casualty insurance business is filled with examples of companies that grew too fast and as a result saw the quality of their book crater as they suffered adverse selection from over eagerness to write new business. But what happens to you if you're not growing and suffer the same fate?

This tends to result in markets where the ability to measure and segment risks is changing rapidly.  Early movers who figure out a better, more precise way to gauge risk engage in price arbitrage against their slower competitors, stealing the better, lower risk business with deep discounts derived from the savings from avoiding the now visible higher risks. The higher risks, facing higher prices inevitably gravitate to competitors who can't yet discern the elevated risk.  So far as we can tell, nothing significant like this has happened for quite some time. It's been so long since there has been major change in risk assessment and segmentation that the industry has assumed it away, focusing their attention on distribution and cost management innovation.  But insurance is the business of measuring, pricing and managing risk. And there are signs that fraud management will drive a comeback in risk measurement and segmentation for competitive advantage.

As everyone says but does little about:  up front underwriting fraud as well as back end claims fraud are big issues, particularly in the Auto Insurance market.  As a result a number of new tools and techniques have emerged that help carriers to screen out more and more dishonest application data and potential claims fraudsters every day. This means that carriers that aggressively focus on fraud and misrepresentation could rather quickly save 5 percent or more of premium. That scale of improvement if pursued systematically, will give them the profitability and flexibility to win the risk segmentation and price arbitrage game.

If it plays out the way I expect then over time more and more carriers will discover this opportunity and adopt new techniques and technologies. But fraud isn't a single "disease" that can be treated with one "cure" but rather a chronic condition with dozens of different and changing ways to deceive. There is no magic bullet.  Instead, fighting fraud is a process of continuous improvement - identifying new threats, making incremental improvements against old ones, measuring success and doing it again and again.  This means that the amount of improvement carriers get is tied to how much effort and time they invest in the process. Laggards will find it hard to catch up on the management of what is a huge cost category.  In the end the Fraud Identification and Mitigation end game will play out much like a game of corporate musical chairs  - as more and more carriers discover and implement the new tools and technologies, the remaining laggards win less of the 'good' business and more of the 'bad' business every month. In the end they will be put in an untenable position with no 'place' left for them in the game.

We're VeracityID and we're an innovator in  real time automated fraud detection, management and mitigation. Our solution: idFusion was developed in conjunction with a top 5 global insurer.  idFusion is a platform that overlays on your existing systems and that can be implemented in a matter of months. This means it can quickly start delivering the results that will allow you to play the Fraud and Errors risk arbitrage game to win.  

Garbage in Garbage out? What happens to real time end to end processing without real time end to end fraud management?

Relentless market forces are driving P&C insurers to make risk-based decisions in real-time, 24/7 across every channel.  And consumers are taking full advantage of the opportunity to shop for deals – with quote volumes increasing even as quote-to-close rates drift ever lower. Ironically, shopping helps them become better information manipulators – rewarding them for shopping even more.  Fraudsters find it easy to hide in this  torrent of fuzzy information, masking their identities and intentions.  

Yet most of the systems and processes FIs employ were designed for a slower era - one in which there was time to assemble and analyze data and make fully informed decisions.  Today, there is simply too much information and too many decisions coming too fast to do business the old way so many insurers are replacing their core systems with more automated, integrated solutions that provide hands free end to end processing.  They have heard the customer's demand for 'fast' and they are responding.

Unfortunately real time quotes without the anti fraud automation to make real time fraud judgments and interventions just means more fraud faster. Indeed automating a process where much of the data is inaccurate or deliberately deceptive is the oldest mistake in information systems, going under the name "Garbage in Garbage out."

Insurers need to solve the accelerated fraud risk problem the same way they've solved the real time response challenge:  with integrated, end to end automation of the fraud identification, intervention and decisioning process. And ideally, this capability needs to be put in place at the same time or even before the real time end to end processing capability goes live. 

Failing to do so would be like building a house without doors or locks: no doubt an impressive structure but you don't dare put anything in it.

Friday, February 12, 2016

Fraud and errors are lumpy and that's a good thing...if you're an anti-fraud leader

We've all heard the narrative: "fraud constitutes from 15 to 20 percent of auto insurance premiums and up front underwriting fraud from inaccurate information on applications averages almost 10 points of that". It's a big, complex problem which is why we at VeracityID have developed a solution that can better identify and manage it.

But while the estimates of fraud incidence are probably reasonably accurate, they really don't reflect the true nature of the problem. Because when actuaries calculate loss prevalence for rating tables they are calculating them based on the total loss (including unidentified fraud and errors) for each granular piece of the market.  And there is reason to believe that honesty and competence and therefore the prevalence of fraud and errors vary widely by sex, age, education, income level, geography, channel and so on. Thus there are parts of the market that likely have very little fraud in them and other parts where fraud could be 30 to 40 percent of total premiums - huge pools of fraud. This creates an incredible opportunity for those who can identify even a fraction of the fraudulent or inaccurate information up front at a granular level.

Here are a few examples where this could be the case. I'm sure you can think of more.

  • How much more prevalent are fraud and errors in lower income, inner city neighborhoods? What proportion of their 'sky high' losses and premiums are fraud and error related? If it's much higher that average, an effective ongoing fraud identification and mitigation program would give a carrier the opportunity to grow rapidly in these communities, helping lower income consumers while getting credit for being a "Social Justice" Insurer.
  • How much more prevalent is fraud via aggregators? What if you could score aggregators by not only your yield but by your fraud-clean yield?  How would that change the way you reward them? How would that change their business model towards you? The same is true of agents. How can you train your channel to send you the 'good stuff' because you can identify a larger share of the 'bad stuff'?
  • How much more prevalent is fraud via the direct channel?  What predictive indicator of web behavior are correlated with inaccurate or fraudulent information submission?  Time? Web v. Mobile Web? Browser? Time spent in session? Commercial, home or school web addresses?  By wireless carrier?  Identifying defects and their costs allow you to continually deepen your segmentation, allowing finer and finer pricing offers.
There's even more:  the greater the variation between the incidence of fraud and other defects from one granular segment to another - the greater the opportunity for early entrants to create huge value.  Because the concentration of fraud means there's a concentration of value to be mined.  And that means that proportionately small reductions in fraud and error incidence can lead to huge pricing and profitability advantages.  For the early mover it radically increases the upside of pursuing a focused, ongoing fraud identification and mitigation strategy like the the one that we deliver via our idFusion Auto Insurance solution.

So fraud is likely to be concentrated in huge 'pools' like giant oilfields.  The 'wildcatters' who to develop the ability to find and exploit them first could reap Texas size share and profit gains. Yee-haw.