Long range Winter forecast 2016/17

The past few days have been distinctly chilly and have fuelled speculation of a harsh winter to come.  After last year’s mild and very wet winter, we look at early indications as to whether this is an accurate reflection.

There is an art to reading and understanding seasonal forecasts issued by the various weather services of the world.   Very few of the available forecasts use the same metrics making a consensus very difficult.

The Met Office released their 3-month outlook the beginning of November and in it they highlighted the risk of a cold start to the winter, but they were quick to point out that “This does not necessarily imply that the UK will experience cold and snow – in fact, the most likely outcome is for conditions to be relatively normal on average over the next 3 months.”

We asked our data partners 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, they report that certainly cold days – and night time frosts – are set to persist for at least another week. According to Steve Roberts of Weathernet this is due to a combination of factors and these include ENSO (El Nino Southern Oscillation) in a neutral state, QBO (Quasi-biennial Oscillation) in its easterly phase, SST (Sea Surface Temperatures – around Newfoundland) that are very warm, and the record lack of Arctic Ice.  So, the odds are already stacked significantly in favour of a December that is considerably colder (and drier) than normal.

Beyond then, from late January into February, things are less clear, or certain – but there are some grounds to believe conditions might revert to stormy and wet, leaving winter 2016-17 as a whole only a little colder and drier.

Beyond then, from late January into February, things are less clear, or certain – but there are some grounds to believe conditions might revert to stormy and wet, leaving winter 2016-17 as a whole only a little colder and drier.

If we do see temperatures as low as those of winter 2010/11, the insurance industry should be ready to brace themselves for a large number of Freeze claims.

5 key benefits of data enrichment for the Insurance Industry

resonateData enrichment provides both insurers and brokers with an opportunity to leverage the vast amount of information they already have and combine it with external data sources to improve business acquisition and enable them to more accurately assess and price risk at the point of quote.

In the past, insurers and brokers had little choice but to rely on information collected at the point of quotation, most often provided by the proposer.  But now with increasing levels of new business being shopped for and written online, there is access to a wealth of public and private data which includes data relating to the individual, their location, property, demographic and lifestyle information.

This data can be used to try and predict customer behaviour, analyse trends, uncover new patterns and improve risk exposure.  Real-time data validation at the point of quote allows additional facts relevant to the risk to be discovered. This has a number of key benefits for insurers and brokers which include:

  1. Increased fraud detection rates

Insurers are experiencing unprecedented levels of application fraud activity. ABI research shows that in 2014 insurers uncovered 212,000 attempted dishonest applications for motor insurance, which is equivalent to just over 4,000 every week.  Statistics show that drivers who lie on their initial application are 66% more likely to make a claim in the future, so the more focus insurers and brokers can put on their initial assessment of drivers, the better.  Patterns, trends and anomalies can be spotted quicker and costs savings can be made by earlier assessments of fraud and identifying early cancellation cases.

  1. Improved competitive position

Data enrichment helps to provide insurers with a single customer view by combining public and private data with quote intelligence.  Insurers are, therefore, able to more accurately assess their customer base and be more selective in terms of the risks they want to underwrite. Thus avoiding poor performing risks and more easily identifying their best customers and those with the highest lifetime value for improved profitability.

  1. Enhanced customer loyalty

Data enrichment can provide insurers and brokers with a richer, deeper understanding of their existing customers. Adding valuable business data to individual records in your database can transform your customer data into customer intelligence. A wider knowledge of your customers’ behaviour and lifestyle means that products can be specifically tailored thereby enhancing customer loyalty and retention.

  1. Greater cross-selling opportunities

A better understanding of your customers leads to more relevant targeting and more opportunity to cross-sell complementary products.  By verifying the customer is who they say they are at point of quote and assessing their credit worthiness, those customers with a higher propensity to purchase add-ons can be identified.

  1. Reduced costs in settling claims

The claims process is time-consuming and demands a lot of resources.  Assessing the propensity of the customer to fulfil their credit commitments at application stage, means that scrutiny of the data at claims stage is reduced, enabling claims to be dealt with quicker, requiring less time and resources to be spent in settling claims and ultimately improving profitability.

The future of data enrichment
In today’s technologically driven society, new ways of exploiting data to gain competitive advantage and new data sources will always be found. Insurers will continue to embrace new data sources and the greater visibility and insight this brings.

Business Insight has a range of products designed to support quote enrichment, risk selection and claims validation as well as the pricing and underwriting of insurance.  We have recently built our own data hub and will be launching the next generation of high resolution property level geographic risk models next year. This will allow users access to more accurate perils information at the point of quote. More details to follow on this in our next newsletter.

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.

The next big climate risk?

supervolcanoes and climate change1816 – the year with no Summer, dramatic climate change and a worldwide recession.  What caused it and could it happen again?

Exactly 200 years ago there was a dramatic change in the earth’s climate. It snowed heavily in July, the River Thames was frozen over, crops failed and there was a worldwide recession. Similar events are believed to have also brought about a dramatic change in climate during the Middle Ages often referred to as the ‘Little Ice Age’. What caused this and more importantly could it happen again?

Scientist believe that the ‘Little Ice Age’ was caused by the cooling effect of a large volcanic eruption or ‘super eruption’.   The last recorded supervolcanic eruption was 201 years ago at Mount Tambora in Sumatra, Indonesia in 1815. It had a massive impact on the world economy due to damage to human life, property, machinery and agriculture and severely impacted the world’s climate for many years afterwards.

Tens of thousands of people were killed by the eruption and in subsequent months, thousands more people died in the surrounding areas from starvation due to the resulting crop failures and disease.    Twenty-four hours after the eruption, the ash cloud that had formed is reported to have covered an area approximately the size of Australia.  This ash cloud took years to clear, changing the climate dramatically and causing a ‘volcanic winter’ that blocked out the sun for between six to eight years.

With the resulting lowering of temperatures, 1816 became known as the year without Summer; with snow drifts on hills until late July and it is reported that the Thames was completely frozen over in September.  There was a subsequent worldwide recession. A similar event happening today would be catastrophic.

supervolcanoesYellowstone National Park, Wyoming, USA has one of a number of active supervolcanoes, although the last eruption is believed to have been over 70,000 years ago.   The United States Geological Survey (USGS) conducted a study on Yellowstone. The study used a program called ‘Ash 3D’ to model the effects of a Yellowstone super eruption, focusing on how much ash would fall, how far it would travel and the major effects it would have on infrastructure.

The study found that cities up to 300 miles away from Yellowstone would be covered by up to three feet of ash.  With the sun not able to penetrate the thick blanket of ash and particles in the atmosphere, the average global temperature would drop by an estimated 10ºC for about a decade which would have a dramatic impact on Earth.  Scientists think that a succession of large volcano eruptions had a similar impact on the climate in the Middle Ages when very severe winters were more frequent.

NASA have also been using state-of-the-art climate models to simulate the response to a major volcanic eruption.  They found that some types of evergreen and deciduous trees virtually disappeared for a number of years due to the lack of sunlight.  However, despite all the scaremongering from the press, the Earth’s climate is more resilient than once thought to a supervolcanic eruption. The research from NASA showed that the climate returned to near normal conditions within a decade in most simulations.

Scientists are continuing to monitor the pressure of underground magma.  From these observations, they have concluded that a large scale eruption is not imminent.  Using various factors and calculations, they suggest a confidence of at least 99.9% that 21st century society will not experience a Yellowstone super eruption.

Insurance and fire risk – 350 years on from the Great Fire of London

fire riskSeptember 2016 marks the 350th anniversary of the Great Fire of London.  The fire, which started in the early hours of Sunday 2nd September 1666 on Pudding Lane and lasted several days, devastated London.

Over 13,000 buildings were destroyed in the fire, including many homes, commercial buildings and other well-known landmarks such as St. Paul’s Cathedral, the Royal Exchange and Newgate Prison.  Miraculously, there was little loss of human life.

As the long and arduous task of rebuilding London commenced, to try and ensure that London would not face such devastation from a fire again, a number of changes were made to laws and Parliament set up the Fire Court.

The Court was established to settle differences arising between landlords and tenants in relation to burnt buildings and decide who should pay.  A year later, physician Nicholas Barbon set up the first insurance company, the Fire Office, whose sole purpose was to insure houses against loss due to fire.

The ABI have calculated that if that particular area of London were to be hit by a similar fire today, repairing the damage caused would cost somewhere in the region of £37 billion.

The insurance industry has come a long way since 1667 but is still dependent on a proper understanding of risks. With ABI figures showing that the average claim for domestic fire damage is around £11,000 and the average claim for commercial fire around £25,000, fire is an important peril for insurance companies to consider.

To help insurance companies better understand their exposure to fire claims and likely accumulations of risk in urban locations, Business Insight has a range of data enrichment models and a mapping and accumulation management application called ‘Location Matters’. The Fire Insight data enrichment models help to assess the relative risk and variation of deliberate and accidental fire claims across the UK; both for commercial property insurance and for home insurance. The models utilise highly complex computer algorithms and vast quantities of data relating to residential and commercial property, the local environment and the demographic make-up by area to estimate risk more precisely.

Accumulation management with ‘Location Matters’ enables an insurer to monitor policy accumulations by location to gain greater insight and understanding of risk exposure, allowing insurers to answer the question ‘should another Great Fire ever happen in London again, what is my probable maximum loss’?

To find out more contact our sales team on 01926 421408.

Product Focus – Escape of Water

perils and escape of waterEscape of Water (Non Freeze) claims currently account for around 25% of domestic claim costs, so having an accurate measure of escape of water risk is vital for insurers.

The cost of insurance claims resulting from escape of water claims such as plumbing equipment failure, and burst pipes and leaks can be significant.   Business Insight’s Escape of Water (Non-Freeze) model has been designed to predict the relative risk of escape of water claims across the UK.

Working closely with a number of insurers and data partners, Business Insight has utilised PhD level mathematical modelling to analyse highly detailed datasets against historic claims patterns to estimate risk by postcode. Over 100 million data records, 26 million properties, 1.7 million postcodes and heavy computing power has resulted in the most detailed project undertaken into this type of insured peril in the UK insurance industry.

Comprehensive information relating to property, the typical demographic make-up of the street and other key predictors has been combined to more precisely calculate the risk of an escape of water claim.  The output provides insurers with a deeper insight into the risk of an escape of water claim for enhanced risk selection and better pricing accuracy.

The model has been independently validated by a number of insurers against their experience data and has shown a high degree of predictive discrimination and potential for use as a rating factor.

Benefits include:

  • Better assessment of risk by location.
  • More precise pricing and rating.
  • Gaining insight into postcode areas where you have no experience data.
  • Discovering where you need to modify your rates to reduce exposure in higher risk areas and to optimise your profitability.

To find out more, please contact us on 01926 421408.

Brexit or Bremain? The results are in…

After months of debating and campaigning on both sides, the results are in and 52% favour leaving the EU.  This was actually something we predicted over a week ago when doing some analysis using our Lifestyle geodemographic classification system, RESONATE©.

The Battle

It was a closely fought battle between the Remain and Leave camps.  Earlier on in the year in February, Remain had held a consistent lead over Leave, with about 55 percent of support according to the polls.  However, the nearer it got to the big day, the more support for the Leave campaign seemed to be growing.  As the campaign progressed, it seemed that a number of factors would affect the result including the turnout, which way the 1 in 10 undecided voters would vote and the weather.

Our Poll

We conducted some analysis to find out which way people would vote and predicted a 53% vote to Leave.   We arrived at this figure by profiling every type of neighbourhood in the UK and each lifestyle category 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.

Our analysis indicated that the battlegrounds of undecided voters were concentrated in areas categorised as ‘Mature Families & Traditional Values’, ‘Wealthy Families in Village, Small Towns and Rural Locations’ and ‘Modern Families, Modest Means’.

The results

As we predicted by using RESONATE©, the result favoured the Leave campaign.  We put this down to a number of factors; firstly, the overall turnout was 72%, higher than the general election. Secondly, some of the areas that favoured Leave were traditional labour heartlands, ‘Blue Collar Heartlands‘ where the turnout was 80%.

We believe that this in the end was a deciding factor. The neighbourhoods more likely to vote leave outnumbered those likely to vote remain based on our database. With a very high turnout the result we predicted proved to be accurate.

RESONATE© is a classification of all households and streets across Great Britain and Northern Ireland and has grouped every neighbourhood into a number of similar categories based on a wide range of demographic, environmental, lifestyle and socio-economic data.

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

Will Summer ’16 bring a surge of subsidence claims?

deckchair squareThere was a lot of speculation by the press after Easter that Summer 2016 would be the hottest for 40 years.  Several statements were made by long range weather forecasting companies in the press that the UK would be headed for a long, dry and hot Summer. In contrast, the long range forecasting model from our data partner Weathernet indicated this Summer to be mild but much wetter than average. Given the extremely wet start to June, Weathernet appear to be right and a surge in Subsidence claims seems unlikely at the moment.

We haven’t had a surge in Subsidence claims for over a decade and these have been more frequent in earlier decades. What should insurers expect when we do get the right conditions for a surge in subsidence claims?

The British Geological Survey (BGS) estimates that 1 in 5 homes (or 6.5 million) in the UK are at risk of subsidence.  Houses built on clay soil are particularly susceptible due to the clay soil shrinking during periods of drought.   It is estimated that around 70% of subsidence claims are as a result of clay shrinkage. Other external causes of subsidence are low rainfall, influence of trees and other vegetation next to properties, leaking drains and erosion due to flooding.

drought smallThe ABI statistics show that UK property insurers receive around 35,000 domestic subsidence claims in a normal year, at a cost to insurers of around £250 million.   With an average subsidence claim having a value of £15,000, insurers need to gain a deeper understanding into the potential risks of subsidence claims.

What can the industry expect in an event year?  The dry summer of 1989 resulted in the number of claims reaching 60,000 for the period 1990-1991.   At this peak, subsidence claims surpassed over £1.1 billion in today’s money for one year. Subsequent hot, dry summers of 2003 and 2006 also led to an increase in subsidence claims and large costs to the industry; with 54,100 claims in 2003 costing an estimated £400 million and 48,000 claims in 2006 estimated to have cost around £301 million.

The construction industry and loss adjusting industry have been become much more efficient at managing claims and carrying out remedial action cost effectively, so the average subsidence claim size has dropped in real terms. However, the same volatile cycle in terms of the number of claims related to weather keeps recurring and when we have had a dry summer this has resulted in a spike in claims compared to the previous year.

Whilst we haven’t experienced an event as extreme in terms of number of claims since 1990-1991, climate change may make claims volumes in the future much more volatile. It is this volatility that can take an insurer by surprise and hit the book hard, turning a promising set of numbers into a poor result for the year.

Legislation relating to solvency requirements and pressure to prove capital adequacy has prompted many insurers to make increased use of mapping technology and external data models to understand their exposure to a ‘worst case’ scenario.  This type of analysis involves an insurer comparing the vulnerability profile of its book of business and its geographic concentration in the context of a ‘worst case’ scenario. The problem is ‘what is a worst case scenario?’

This question is difficult to answer and would be slightly different for each insurer as it would need to be answered in the context of the property profile of each insurer’s book as this would have a marked effect on the degree of vulnerability to subsidence risk. Property vulnerability and understanding which policies are prone to making a claim is a large part of the overall risk profile. For example, it is worth making the point that areas of modern housing are much less likely to be affected. Also areas of older housing that have been hit in the past will have had the most vulnerable properties strengthened via partial or full underpinning. New properties are built to different standards with deeper foundations than certain older properties and so in general have lower vulnerability. Property type is also important, for example, single storey dwellings or Bungalows are lighter structures and so in general these are more vulnerable to damage through smaller amounts of ground movement than say a 2-storey or heavier structure.

Business Insight use detailed property data together with vegetation and tree data, geology, long term climate data and claims to model the level of subsidence risk for insurers. ‘Drought Insight©’ is licenced by a large number of household insurers and is recognised as the market leader in providing insurers with a deeper understanding of exposure to drought related subsidence claims.

For more information about managing subsidence risk, contact us on 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 – Accidental Damage

Gain an unrivalled perspective into the distribution of accidental damage risk across the UK

Business Insight has launched a new data model to help predict the relative risk of accidental damage claims across the UK covering lifestyle, property and geodemographic incidents.

Working closely with a number of insurers and data partners, Business Insight has utilised PhD level mathematical modelling to analyse highly detailed datasets against historic claims patterns to estimate risk by postcode. Based on a large sample of actual claims experience data, Business Insight’s AD Insight© uses the latest technology to analyse claims and predict annualised claims frequency by postcode unit.

This model outputs have been independently validated and tested against insurer experience data and have shown a high degree of predictive discrimination and potential for use as a rating factor.

The state-of-the-art maths modelling and computing power behind the model means that the model allows its users to extract the maximum predictive potential from the underlying data.  You can quickly discover how your rates compare in the low and high risk areas.  AD Insight’s powerful modelling capabilities provide users with:

  • Enhanced understanding of accidental damage risk
  • More accurate underwriting of accidental damage risk
  • Better decision making on risk selection, valuation and pricing.