Profiling can help you understand your customers and prospects and assist with predicting their propensity to buy a particular product line or to shop at specific locations.
For consumer scenarios, there are a range of neighbourhood profiling products including data sets such as PERSONICX GEO, P² PEOPLE & PLACES, ACORN and CAMEO for UK & many different countries in the world.
These data products are created by cluster analysis of the whole country.
They
group together areas where for example, there are likely to be lots of married professionals living in semi-detached housing, owning more than one car with a high ownership of credit cards. People in households in these particular areas are also likely to be interested in the theatre, home computing and taking foreign holidays.
|
Other clusters might identify areas where there are lots of low income retired people with a high incidence of smoking and interest in Bingo, horse racing etc.
In Britain, each unit postcode is allocated to the cluster which is most likely to describe the majority of households within the postcode so you can take your customer mailing list and append a cluster code to each one. Then you can total the number of each type, buying each of your products to look for trends. For example you may be promoting a traditional budget priced product that is more attractive the older low income groups.
Using GeoConcept, you can identify areas where there are concentrations of the type of person you are hoping to target.
Or you may not have a mailing list to profile, but know which of your existing outlets or franchisees are doing really well. |
Using GeoConcept you can select all the profile records within the franchise area or within a specified drive time of your outlet, to profile the outlets that do well.
Then when you are assessing new sites, you can compare the profile of the new catchments to those of existing outlets in order to predict whether the new site is likely to be successful.
In addition to general consumer profiling there are datasets offering clustering detail according to house prices, household income, interest in financial investment products etc. |