Sweating your data assets
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 who live there. These type codes were primarily intended for marketing purposes, but they can also be used directly in mortality analysis and underwriting. Geodemographics are also a powerful cost-benefit proposition: marketing departments often already have a geodemographic licence, so the extra cost of using it for underwriting and mortality modelling can be zero. Getting more value out of your current spending is perhaps the defining hallmark of these straitened times.
So geodemographic profiles can be very cheap indeed, but why can they be useful? The answer is that they contain a lot of mortality-relevant information which would be time-consuming and expensive to collect directly. By way of illustration, nobody nowadays disputes the mortality risks associated with smoking. The following table shows the scores for smoking and limiting long-term illness for the P2 classification from Beacon Dodsworth:
Table 1. Propensity scores for P2 classifications A-M (100 = population average)
| A | B | C | D | E | F | G | H | I | J | K | L | M | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Smoking | 54 | 80 | 69 | 89 | 87 | 68 | 105 | 114 | 104 | 145 | 139 | 166 | 122 |
| Illness | 57 | 74 | 51 | 81 | 58 | 92 | 100 | 83 | 122 | 143 | 165 | 169 | 220 |
Of course, knowing that someone's postcode falls into group L does not tell us if they personally are a smoker or non-smoker. However, we can say that they live in an area where smoking is over three times more prevalent than in group A. This is obviously useful where knowledge of actual smoking status is unobtainable or uneconomic to collect, such as bulk-annuity business. Since postcodes are collected anyway as part of normal insurance business, it makes sense to squeeze the maximum value out of them.
Add new comment