Blog: Getting to grips with the quote manipulation data to combat fraud

With up to 90% of motor insurance sales originating online, quote manipulation has become a growing challenge for insurance retailers, and one that has historically been difficult to detect and address pre-sale, due to the sheer volume of quotations being generated.

The Hummingbird Syndicate was, therefore, launched in the summer, bringing together major insurance brands to benefit from sharing quote manipulation insights garnered using data intelligence. This aims to help insurers tackle an issue which has come to the fore in a perfect storm of conditions.

These include the de-personalised nature of online shopping, the escalating cost of motor insurance, the availability of guides to ‘help’ consumers bring down their premiums by considering how they enter data and the ‘grudge purchase’ factor. Surveys suggest that over one-third of consumers believe that manipulating data fields is an acceptable way of reducing their insurance premiums.

The scale of the challenge in pinpointing fraudulent behaviour is evident in the numbers: in its first 30 days, the syndicate processed data relating to over 15 million motor insurance quotes to over three million consumers.

Legitimate experimentation or suspicious behaviour?

The anonymity of the online channel and the corresponding temptation for people to experiment with factors that affect their premium is well documented. This propensity is corroborated by the Hummingbird data, which shows that almost half of the consumers in the sample varied at least one risk area between quotes and requested, on average, over five quotes when shopping for car insurance. So which risk factors are people changing?

The most frequently adjusted field is ‘annual mileage’, altered by 27% of people, closely followed by licence duration and occupation. This of course includes consumers processing perfectly legitimate ‘what if’ quotations, as well as those looking to game the system.

When changing annual mileage details, nearly one-third entered two or more values and over 5,000 people made five or more changes. No claims bonus changes also featured highly, with over 20,000 people making changes involving a variance of nine years. It is clear why this may be suspicious, especially when multiple changes span a number of different risk factors.

The data also shows an interesting relationship between the number of different risk factors people amend when requesting multiple quotes and the overall number of individual changes they make. This peaks at four risk factors. In other words, people whose changes involved four risk factors made the highest number of overall changes.

Midnight manipulators

There are also insights into the times when people are more likely to be engaging in quote manipulation. While the overall peak time for requesting a motor insurance quote is 4pm, when the results are filtered to include only people who had made a significant number of changes to their quotes, suddenly peaks in the early hours of the morning are visible.

Clearly, there is now significantly more insight into consumer behaviour, and the key for retailers is that this information is available in real time, as it happens. This enables action to combat fraud to be taken pre-quote, reducing cancellation costs and helping insurance providers to secure the correct price for the correct risk.