How not to do postcode profiling

(Jun 15, 2011)

We have written extensively about how to use postcodes for mortality modelling.  The best approach in the UK is to use so-called geodemographic profilers, which map postcodes to relatively homogeneous groups of households sharing certain socio-economic characteristics.  This approach uses the full, two-part UK postcode, which is often sufficiently accurate to pinpoint a residential street.  We have both an A4 flyer and a short web video which introduces newcomers to the subject.

However, it is often instructive to look at mistakes.  Somewhat surprisingly, there are still so-called "postcode mortality" tools which make the error of assuming that the first part of the postcode is all that…

Read more

Tags: postcodes, geodemographics

(Not) Falling for the Fallacy

(Jul 26, 2010)

An important concept is demography is the ecological fallacy.  This is where aggregate data for a group are used to draw erroneous inferences about individuals belonging to the group.  The less well known flip side to this is the atomistic fallacy (or individualistic fallacy), where attributes of individuals are used to make incorrect generalisations about the group to which they belong.

A related example of this was illustrated in an earlier posting on the link between smoking propensity and geodemographic type.  In the P 2 classification, people in category L were three times more likely to smoke than people in category A.  People in category L therefore tended to have higher mortality and didn't live as…

Read more

Tags: ecological fallacy, smoking, geodemographics, asbestos

Health of the Nation

(Jan 21, 2010)

Geodemographic profiles use addresses or postcodes to classify people into groups which are homogeneous with respect to variables like income, housing tenure and life stage.  The original purpose of geodemographic profiles was to improve targeting for marketing purposes.  There is no point in sending marketing material for hearing aids to young families, for example, and geodemographic profiles help make more efficient use of marketing resources.

Geodemographic profiles have been conclusively shown to be predictive of mortality in the United Kingdom, both by Richards (2008) and Madrigal et al (2009).  This is because geodemographic profiles are about education level, wealth and income (amongst…

Read more

Tags: geodemographics, Acorn, Health Acorn

Island Life

(Nov 10, 2009)

We have written extensively about the use of postcodes and geodemographics for mortality modelling.  Two peer-reviewed papers recently presented to the Institute of Actuaries in London have testified to the power of geodemographics when applied to pensioner mortality: Richards (2008) and Madrigal et al (2009).

One feature of standard U.K. postcode profilers is that they typically exclude the crown dependencies, which are not legally part of the United Kingdom.  This makes it impossible to assign a geodemographic type, despite the fact that crown dependencies often have a postcode system which follows the same hierarchical structure as that of the UK.  Postcodes for crown dependencies are therefore…

Read more

Tags: postcodes, geodemographics, Mosaic, Acorn, Guernsey, Jersey, Isle of Man

Part of the story

(Oct 9, 2009)

The Institute of Actuaries' sessional meeting on 28th September 2009 discussed an interesting paper.  It covered similar material to that in Richards (2008), but used different methods and different data.  Nevertheless, some important results were confirmed: geodemographic type codes are important predictors of mortality, and a combination of geodemographic profile and pension size is better than either factor on its own.  The authors also added an important new insight, namely that last-known salary was a much better predictor than pension size.

The models in the paper were GLMs for qx, which require complete years of exposure.  The authors were rightly concerned that just using complete years would…

Read more

Tags: geodemographics, GLM, survival models, UDD, Balducci assumption

A Scottish question

(Sep 2, 2009)

The Scots are an innovative bunch, including the inventor of the telephone and the discoverer of penicillin.  Not all of our innovations have been positive, however.  Human welfare did not advance with the invention of the deep-fried Mars bar, for example.

With such dietary crimes it comes as no surprise that the Scots are known for having the shortest life expectancy within the four countries of the United Kingdom.  This even extends to select sub-groups, such as the portfolio of pension annuitants behind Table 1.

Table 1.  Time lived between ages 60 and 95 for males in United Kingdom (curtate life expectancies for holders of pension annuities).

Male life

Read more

Tags: Scotland, region, geodemographics

How wrong could it be?

(Apr 23, 2009)

We have written previously about the importance of the independence assumption when modelling mortality for annuities and pensions. In a recent presentation to the Royal Statistical Society I showed the audience how life insurers deduplicate their annuity data and how they use postcodes to identify socio-economic status.

When I pointed out the strong link between income, status and multiple policies, a member of the audience asked about the impact of failing to deduplicate. This is an interesting question, since getting mortality assumptions correct for annuity pricing is particularly important due to the great sensitivity of profitability on reserve levels.

We therefore fitted a simple Perks model…

Read more

Tags: deduplication, mortality, annuities, geodemographics, Mosaic

Sweating your data assets

(Apr 16, 2009)

In recent years insurers have looked to making better use of the data they already have. The appeal is simple: if you have already collected the data, then it is like leaving money on the table if it is not being exploited to the full. Worse, if your competitors make better use of their data, you can be selected against and lose money.

The biggest change has been in insurers' attitude towards the use of postcodes. Postcodes have to be collected and maintained anyway as part of normal business, so any extra value which can be squeezed out of them is a low-cost bonus.  As we will see, this can sometimes even be a zero-cost bonus.

Every UK residential postcode can be assigned a geodemographic type to describe the sort of people…

Read more

Tags: postcodes, geodemographics, smoking, missing data, P-squared

Size isn't everything

(Dec 9, 2008)

In an earlier post we discussed the correct way of using postcodes for analysing mortality, and also how this works in countries outside the UK.  It is worth re-iterating why insurers use so-called geodemographic profiling.

The first point is that the more risk factors in your underwriting model, the less likely an insurer will be selected against in the market.  For example, if you price annuities just using age, gender and fund size while everyone else uses the same three plus postcode, you will lose money due to the relative lack of sophistication of your underwriting model.  The richer your underwriting model, the less scope there is for being selected against by the rest of the market.  Indeed, if your underwriting…

Read more

Tags: postcodes, geodemographics

Modelling and the Maple Leaf

(Oct 10, 2008)

We get a lot of interest in our software from Canada. We don't know specifically why this might be - despite that fact that two of our founders are Scottish, we are not aware of any distant relatives still panning for gold out there.

One possible reason is that Canada, like the Netherlands, USA and the UK, has a hierarchical postal code with fine granularity.  This makes Canadian postcodes highly amenable to profiling for socio-economic status, and therefore useful in modelling longevity, persistency or any other decrement influenced by wealth and lifestyle factors.

Statistics Canada keeps tabs on the number of active postal codes, estimated at around 861,000 and shared across a population of around 33 million…

Read more

Tags: postal code, postcodes, Canada, geodemographics

Older Posts »

Find by key-word

Find by date

Find by tag (show all )