When adverts know who you are

Could advertising hoardings and vending machines become smart enough to know who you are? New developments indicate that they will soon be able to market to individuals based on personal characteristics, potentially increasing revenues for their users.

One good example is CognoVision, a company recently acquired by Intel, which has developed face recognition software able to determine a person's approximate age, along with their gender. The idea is that wall-based advertising displays could assess the type of person looking at them, and tailor advertisements accordingly. So, a young woman might see advertisements for makeup, whereas an older male might be shown aftershave or cars.

This could crack one of the biggest criticisms of advertising posters, which is that they don't target anyone in particular, other than the people most likely to be walking past them.

Of course, this presents its own problems. Many people see lots of posters as they walk past in the crowd, for example. And presumably, a young man Christmas shopping with his mother who stops to take a look might confuse the system. Nevertheless, the company claims accuracy rates between 85 and 95%.

The real benefit here could come with more interactive advertising displays or vending machines, which require a customer to do something rather than stand and stare. Drinks machines are a good example. The JR East Water Business Company has installed a drinks machine that determines the age and gender of the customer and makes drinks recommendations based on what is known to sell to certain demographic groups. Apparently men prefer canned coffee drinks, and women prefer tea.

Anthony Plewes

After a Masters in Computer Science, I decided that I preferred writing about IT rather than programming. My 20-year writing career has taken me to Hong Kong and London where I've edited and written for IT, business and electronics publications. In 2002 I co-founded Futurity Media with Stewart Baines where I continue to write about a range of topics such as unified communications, cloud computing and enterprise applications.