Using big data in the UK to classify residential neighbourhoods

resonateBig Data analytics is having an impact in many areas of industry. In the recent race for the US Presidency, it played a key part in Trump’s success. While the media in the US was consistently predicting a Clinton victory, behind the scenes it is reported the Trump campaign were employing an army of Data Scientists to crunch huge amounts of social media data using Artificial Intelligence (AI) (machine learning techniques) to work out who the marginal voters were. Looking at what people were doing, saying and communicating, they homed in on what key issues were most important for particular individuals, classifying them and then working out what messages they needed to target them with. Whether or not this was decisive is unclear, though it certainly will have had some influence on the numbers and the Trump victory.

Modern analytics allows us to combine large amounts of data from lots of different sources and use machine learning and AI techniques to convert this vast amount of data into meaningful insights to base informed decisions upon. Business Insight has built its own AI machine learning platform called ‘PERSPECTIVE’ to crunch huge amounts of data to produce estimates of risk or likely outcomes. Big data analytics in the insurance industry has a number of benefits for insurers; one of which is helping to understand customers better, others include helping to improve pricing, rating and underwriting through a greater understanding of risk.  It can also tease out hidden patterns and provide insights that may otherwise stay hidden.

The amount of data may have increased enormously in recent times though making sense of large volumes of demographic data and pigeonholing people is not something new.  A geodemographic classification assigns geographic areas to categories based on the similarities across a vast range of different variables. It is a structured way of making sense of complex and very large socio-economic datasets.

Streets and neighbourhoods can be classified into types such as ‘Affluent Achievers’ or ‘Comfortable Greys’ in wealthy areas through to types such as ‘Breadline & Benefits’ in more deprived areas. The products are based on the assumption that people living in similar housing and sharing similar characteristics across a range of factors relating to age, affluence, family composition and life stage are likely to have similar wants, needs and exhibit similar behaviour.

Geodemographic classifications have been around and used in industry for a very long time. The origins in the UK can be traced back to Charles Booth who analysed the 1891 UK Census and produced a classification of streets throughout London with neighbourhood types such as ‘Lowest Class. Vicious, Semi Criminal’ – not labels that would be palatable nowadays, even if accurate. With the arrival of the computer and as access to large amounts of data increased, we saw the emergence of commercial classifications in the 1970s with PRISM developed by Claritas in the USA and ACORN (A Classification of Residential Neighbourhoods) developed by CACI in the UK. The first versions developed in the 1970s were built from Census data and used by marketing departments to target product offerings more accurately. Since then the complexity, amount of different data sources used and the level of granularity has increased dramatically, as has the number of different commercial uses that the products are used for from advertising and target marketing through to analysing crime patterns and health resource requirements.

There are many different ‘lifestyle’ or ‘neighbourhood’ classifications though most are general purpose, i.e. they have been built with no specific industry or use in mind so can be useful across a range of industry sectors and for a range of purposes. In contrast, the ‘Resonate’ classification developed by Business Insight has been built with the insurance industry in mind. So for underwriting and pricing insurance, Resonate will offer more discrimination than the general purpose systems available in the market. With the ever increasing volumes of data and available computing power, risk models and lifestyle classifications are becoming more focused and more accurate.

With the ever increasing volumes of data and available computing power, risk models and lifestyle classifications are becoming more focused and more accurate.  Clever use of data and analytics can give companies a competitive edge, help to ensure you are not selected against and as we have seen, sometimes, lead to surprising results!

Click here for more details on Resonate or contact us at 01926 421408.

BREXIT? A view on the result using RESONATE Lifestyle data

Brexit squareWith the Brexit vote about to take place this week we thought it would be interesting and also a bit of fun to use our RESONATE geodemographic classification system to give an indication of the likely result.

Looking at every type of neighbourhood in the UK we estimated which way each lifestyle category is likely to vote based on media reporting and analysis. This was then scaled by the distribution of voters within each category in every street across the United Kingdom and Northern Ireland.

The analysis seems to indicate that the battlegrounds of undecided voters are concentrated in areas categorised as ‘Mature Families & Traditional Values’‘Wealthy Families in Village, Small Towns and Rural Locations’ and ‘Modern Families, Modest Means’.

Targeted communications aimed at these neighbourhoods might have reaped better rewards for either side in their respective campaigns. The analysis predicted a 53% vote to Leave. Although a high turnout is expected, there will be variation across the geodemographic categories which has not been considered and also there will be some statistical error within this analysis. So it could still be a vote either way.

For more information about RESONATE Lifestyle & demographic data, contact us on 01926 421408.

Product Focus – BRICKS

BRICKS imageDo you know how accurate the reinstatement values of the buildings insurance policies on your book are? Do you know which are under insured?

BRICKS© is a new model that calculates the reinstatement values to rebuild typical properties by postcode unit and address across the UK.  Based on detailed research, reliable data and a sophisticated quantity surveyor pricing model, BRICKS© provides insurance professionals with accurate rebuilding estimates.

The model estimates the rebuilding costs across a vast range of different property types spanning one bedroom bungalows through to six bedroom detached properties. The demographics, property characteristics and level of affluence in each postcode are all assessed to gauge the quality as well as the size of a total rebuild.

For an insurance intermediary, this can help in advising clients on an appropriate minimum rebuilding cost with a quick, readily available estimate of the level of cover sufficient for the risk.

For the insurer, it can help to ensure they are more competitive for risks where current reinstatement values are too high and are not missing out on additional premium where reinstatement values are too low.  For reinsurance, it also provides a more accurate assessment of the aggregate risk across your book and a more accurate measure of exposure to feed into property catastrophe models.

It has been tested, validated and subsequently licensed by several insurers. They found a startling uplift on testing BRICKS© against their own experience. It also showed added value over similar products available in the market.

Easy to use and supplied in a number of formats to fit seamlessly into your existing systems, BRICKS©allows you to simply input the location and property details and quickly discover what the typical rebuilding cost or reinstatement value should be for that particular property.

Benefits include:

  • Gain a quick, economical and precise check for under-insurance.
  • Advise your customers on an appropriate level of cover as a basis for your quotes to ensure the best service is being delivered to your client base.
  • Find out where policyholders are under-insured to justifiably propose an increase in cover on renewal.
  • More accurate rebuilding cost estimates assist in understanding in more depth the risks on your book to help with reinsurance needs and solvency II requirements.
  • Discover where you need to adjust your notional sums insured for bedroom rated products to make sure you are competitive in cases where your current estimates are too high.

For more information on how BRICKS can add value, please get in touch with us on 01926 421408.

How insurers can assess flood risk more accurately

The impact of Storm Desmond on the 4th and 5th December 2015 with gale force winds and unprecedented rainfall has resulted in severe flooding in Cumbria and the North of England. UK insurers will be faced with a large bill as a result with initial market loss estimates being put at up to £500 million.

The bad news for insurers is that these extreme weather events are not going to go away.  With around 5,200 residential properties flooded, the estimated bill to the insurance industry in terms of household claims is thought to be around £174 million.  Every model that has been produced indicates that we are going to be experiencing more severe weather conditions in the future.  So what can insurers do to mitigate their flood risk exposure?

Property risk in the insurance industry depends on a range of factors linked to the physical location. The local environment, the types and construction of buildings, local crime rates, the demographic make-up of the population, physical hazards such as flooding, storm or extreme cold weather – all need to be considered when assessing each risk.

There have been some significant developments over the last few years in terms of the data and tools available and insurance companies are now able to make insightful decisions based on reliable data and risk mapping software.   Things have moved on from rating at the level of postcodes to using more sophisticated methods which allows rating at an individual address level for risks, enabling insurers to understand their exposure to a much greater depth.

Business Insight’s risk mapping tool, Location Matters©, combines state-of-the-art risk mapping technology with the best of breed perils and geodemographic data to provide insurers with a powerful insight and a deeper understanding of geographic risk and the make-up of the local area.

It is the only mapping software designed specifically for the insurance industry that features a complete set of best of breed perils risk models including the market leading Business Insight data models for the UK property insurance market and JBA Flood data.

Location Matters© provides today’s insurance professional with the highest resolution data to give them a greater insight to risk, help drive a more profitable risk selection and improve exposure management through insight into accumulations of risk across their book of business.  It can also be used post an event within Claims Departments to assess the validity of individual claims and for better allocation of resources.

We are still learning about the future implications of climate change, but one thing seems certain – weather conditions look unlikely to stabilise.  The potential influence of climate change cannot be ignored as even small increases in the frequency and severity of events can translate in to significant numbers of claims.

So it is more important than ever for insurers to invest in technology and data models that are based on up-to-date, reliable information that take in to account changing risk patterns to gain a deeper insight into risk.

Find out more about Location Matters© here.

Product Focus – RESONATE

RESONATE© is the latest analytics data product from Business Insight and was launched earlier this year.  It is a very detailed model classifying demographic, neighbourhood and lifestyle information into distinct risk categories at a highly granular level.  It is the only geodemographic classification system enhanced specifically for the United Kingdom personal lines insurance market.

RESONATE© classifies people on the demographics of the neighbourhood in which they live.  Featuring easy to understand segments and classifications, it has been built from a wide range of data sources including the latest census information and environmental risk factors as well as data relating to lifestyle and affluence.

Providing insurance professionals with a wide range of analysis options, RESONATE© consists of over 1000 different demographic clusters, ranked into relative affluence.  These clusters have then been grouped into a more easily manageable 50 distinct Neighbourhood Types that fall into 11 Lifestyle themes ranging from ‘Affluent Achievers‘ through to ‘Breadline and Benefits‘.

For example, the Lifestyle Group ‘Affluent Achievers’ makes up 7.4% of all UK households and within this group there are a number of distinct neighbourhood types such as Type 1 typically found in Kensington and Chelsea. This neighbourhood type consists of very wealthy mature families and couples, privileged lifestyles and high value homes located in exclusive urban areas and makes up less than 1% of UK households. Within the same Affluent Achievers group we also have Type 5 prosperous professional families with young children living in large modern housing. This neighbourhood would also be categorised as one of the ‘mass affluent’ segments of the UK demographic make-up with high disposable income, private schooling, large housing and highly paid professional and white collar managerial occupations being key characteristics. Type 5 represents 2.3% of UK households and can be found in high concentration in locations such as St. Albans, Wokingham and Berkhamsted.

The geographic segmentations have been developed to help analysts, underwriters and marketeers to:

  • Get another insight into risk pricing from another lifestyle and demographic perspective.
  • Understand the business’s current market penetration across segments.
  • Track product uptake trends across their customer base for future product builds and marketing offers.
  • Understand customer’s behaviour towards price in a competitively priced market.
  • Provide a risk assessment of their customers based on their claims frequency and average claims value.
  • Identify segments of higher margin/less risk customers and build strategies for retention and new customer acquisition.
  • Help offer the right products and services to the right customers and better match offers to demand.
  • Identify segments of loyal customers.
 Find out more about RESONATE© here  or contact the Business Insight team for a demonstration on 01926 421408.

Weather warning?

Is the media speculation correct? Are we really heading for the coldest winter in 50 years? Is the media speculation correct?

The weather over the last year has been fairly benign with associated claims being well below historic averages. When can we expect to see another major weather event? Various news sources have been speculating that Britain is set to be battered by fierce snowstorms and freezing temperatures this Winter as the first El Niño cycle for five years kicks in.  But with the Met Office reporting that 2014 was the warmest year on record and 2015 shaping up to be warmer can we predict with any accuracy what is more likely?

Whilst there have been no major weather events for a while and claim levels low, let us not forget the impact that a severe weather event can have. The last El Niño event was the winter of 2010 which was the coldest since records began and during that period the ABI reported receiving over 467,000 claims affecting vehicles, homes and businesses.

Of those claims, 190,000 related to property damage at a cost to the industry of £900 million with 103,000 accounting for burst pipe damage.  A further 278,000 were linked to vehicle damage costing £530 million.

A strong El Niño event doesn’t necessarily correlate to a severe Winter for the UK, however, and our data partners at Weathernet have produced a graph to illustrate the relationship between Winter Severity and El Niño events (highlighted in purple). The Winter of 2006/07 is a perfect example of an El Niño event when the winter weather was remarkably warm.

We asked the experts at Weathernet, if there were any indicators to suggest we are heading for the severe winter the press is speculating about.  The Weathernet team advise that beyond two weeks ahead, all forecasts should be treated as very speculative. However, the outlook from their long term model looking forward until March suggests that temperatures are likely to be milder than average this winter but they expect it to be wetter and we are likely to get much more rainfall.

Compared to historic averages, they are forecasting over double the average rainfall in many areas of East Anglia, the Midlands and the South East of England. More rain days than average are also expected in the South East of England and a consequence of this could be higher than average claims for flooding in areas at high risk.

The Met Office 3-month Outlook and their seasonal prediction system also suggests that above average rainfall is more likely which may also be coupled with an increase in the frequency of Atlantic storms and spells of windy or stormy weather.  The winter period from December 2013 to February 2014 was the wettest on record. A repeat this winter would result in a surge in storm and flood claims and an Industry bill approaching the £1 billion mark.

In contrast to this view, Piers Corbyn of WeatherAction, an expert in long range weather forecasting based on solar activity, is predicting that in the run up to Christmas, Britain will be very cold and have heavy snow, especially in the North East.

Extreme weather and severe events like the winter freeze of 2010 are difficult to predict in advance. However it is possible through analysis of vast volumes of historical data to understand and highlight the areas that are more at risk. Investing in technology and data models that are based on accurate, up-to-date information and that take account of changing risk patterns to gain a deeper insight in to risk is becoming more important for insurers to ensure they are not selected against or over exposed in high risk areas.

Greater demographic insight is now possible with the launch of RESONATE – a new data tool from Business Insight

Resonate_LogoRESONATE© is Business Insight’s newly launched geodemographic classification of all households and streets across the UK and Northern Ireland.   Every neighbourhood has been grouped into a number of similar categories based on a wide range of demographic, environmental, lifestyle and socio-economic data.

Benefits to insurance professionals include:

  • Deeper insight into risk pricing from another lifestyle and demographic perspective.
  • Understand the business’s current market penetration across segments.
  • Model and visualise customer demographics in specific areas for more accurate policies and quotes.
  • Easily identify segments of higher margin/ less risk customers.

Read more here: Press release 25th March 2015- RESONATE

Post Magazine Article: An Era of Androgyny

With gender set to disappear from the underwriting landscape at the end of 2012, what factors will insurers turn to when accessing risk?

The Post discuss the new genderless rating environment and how insurers are working frantically to adjust the way they price their risks. Mark Harrison, our MD, is quoted.

Read More here: Post Magazine Article 2 February 2012

Business Insight hires leading analytics industry specialist

MasterBusinessInsightLogoBusiness Insight is delighted to announce that Dr. Alan McLachlan will be joining the team as Analytics Technology Principal to support the further development of its risk assessment product suite.

Alan is a highly experienced analytics and technology specialist and previously worked in a senior consulting role for Vodafone and before that in a number of senior roles at blue chip companies. Prior to that, Alan worked in academia as a research fellow studying Quantum Theory and he holds a PhD in Physics, an MSc in Neural Computing as well as achieving a first class Physics degree.

Read press release here: Press Release – Business Insight hires Analytics Principal 120912

Post Magazine Article: Sharing is Caring

Data sharing among insurers offers a range of benefits – but could firms’ desire to retain a competitive edge hamper such collaboration?

With an increasing amount of data available to insurers to help combat fraud, underwrite appropriately and improve claims handling, the question of how information should be used has never been more pertinent.

Read Article here: Post Magazine 8-11-12