Articles - Discovering insurance data insights

The factors that go into understanding insurance risk are growing. New data insights are emerging to provide a much clearer, multi-dimensional-like view of each risk to help price fairly and appropriately and support customers based on a fuller understanding of their needs. Thanks to these developments, the broad assumption that an individual is a higher risk because they have had a prior claim may no longer stand.

 By Eleanor Brodie, Manager, Data Science, UK and Ireland at LexisNexis Risk Solutions

 Insurance providers today have access to data attributes about an individual, an asset such as a vehicle, a business or property – all from one access point - that offer a much deeper understanding of risk, allow enhanced personalisation, expedite the quote process and improve pricing accuracy. The growth of insurance specific data attributes has only happened relatively recently, over the past five or six years. This is thanks in large part to the growth of market-wide contributory databases where insurance providers share policy history, quote and soon historical claims data.

 The sharing of this data is just the start. By applying data analytics skills, it then becomes possible to uncover correlations between policy, quote and claims behaviour with claims losses, adding to the overall picture of risk.

 One of the areas in which this multi-dimensional data approach is well-advanced is in private motor. Insurance providers can now understand at the point of quote an individual’s No Claims Discount (NCD) entitlement, the risk of policy cancellation and their predicted claims cost relative to how they have managed their motor insurance policies in the past.

 Motor insurance providers can also identify potential named driver fraud, such as fronting for a younger driver in the household, and the risk of ID fraud via email address intelligence. Bringing in data about the vehicle build, providers are also now starting to understand the Advanced Driver Assistance System features (ADAS) fitted to an individual vehicle – both standard and those chosen as optional extras - and then how they correlate to claims.

 These insights are far from being ‘happy accidents’. They all solve specific pain points for the market and were uncovered by data analysts for that specific reason. Cancellations are costly for the market; named driver fraud can leave unwitting motorists exposed; NCD proof on paper was inconvenient for the customer and an admin headache for the insurance provider; and ADAS is described in many different ways making it a blind spot for insurance rating.

 In a post-pandemic world, the emergence of these new insights takes on new relevance. It is only by virtue of the fact that the market shares data that it has become possible to understand policy, quote and claim behaviour directly related to lockdown periods. This, for example, is enabling insurance providers to view a cancellation in lockdown distinct from a cancellation outside of that time.

 So, finding the next big data insight starts by understanding the pain point then working back to understand how and when data could be used as a solution.

 At LexisNexis Risk Solutions, the process of validating an idea for a new data attribute starts with the data science team building an analytical prototype with the appropriate data sources and outcomes. Once the concept is proven and we feel the market opportunity exists, we create the final specs for technology to implement. A crucial part of any new data attribute is testing with insurance providers to demonstrate the value of the new data attribute on the insurance provider’s own data. This process can take different forms - we may create actionable insight studies to benchmark performance or perform retro validation tests as part of a batch process.

 As that work reaches completion and we are confident the new data solution will deliver what the market needs, we look at any required regulatory documents on the solution inputs, outputs and overall performance. Once the product starts to roll out, the process of validation continues for new insurance providers interested in testing the data solution for themselves. Crucially, the data attributes are monitored on an ongoing basis to help ensure they continue to perform as expected.

 Contributory databases have created some of the biggest insights coming into the UK insurance market in recent years. However, there is a constant process of evaluating new potential data sources for product development as well as to enrich existing solutions.

 The key is to deliver data to the market in a way that is useable and actionable, whether that’s at application, point of quote, renewal or claim.

 Fundamentally, with the growth in data sources and new data attributes, the better insurance providers are able to understand, segment and price their customers, to ensure the fairest treatment possible, which can give them a leg up on the competition. Understanding risk has become so much more than claims history.


Back to Index

Similar News to this Story

Will general election call shake up pensions policy agenda
With the Prime Minister calling for a summer election, LCP Partner David Fairs looks at how this could affect the pensions policy agenda. What does th
Risk Transfer do more insurers mean more capacity
Nikhil Patel takes an in-depth look at current trends in the risk transfer market, including the implications of record-breaking demand and how new en
Aiming for calm seas in our market reforms
The size and scale of the UK financial sector is worth reflecting on. It employs more than 2.5 million people and produced £278bn of economic output,

Site Search

Exact   Any  

Latest Actuarial Jobs

Actuarial Login

 Jobseeker    Client
Reminder Logon

APA Sponsors

Actuarial Jobs & News Feeds

Jobs RSS News RSS


Be the first to contribute to our definitive actuarial reference forum. Built by actuaries for actuaries.