Saturday, April 12, 2014

How to increase ad response up to 15% through facial selection

Having worked in advertising and direct response for most of my career, I am very aware of how difficult it is to create an effective promotional piece.  It's about one half science and one half trial and error.

So when a new science based technique is introduced that offers to increase response by a whopping 15%, professionals in the field sit up and take notice.  To put this in perspective, through dint of effort we were able to increase response by one or two percent, that was a major accomplishment.  Five percent and our clients thought we could walk on water.  Fifteen percent? Almost unheard of since the day N.W. Ayers invented the ad agency just after the Civil War.

So what is this technique?  It's facial selection, not through trial and error, but through facial recognition software as used by law enforcement and security organizations.

Here's the story:

Merely changing the face of a model in an ad increases the number of potential purchasers by as much as 15 percent (8 percent on average), according to a study. The study shows that a technique to screen faces when designing ads can transform the current subjective process into a scientifically automated one. Considering the extensive use of human faces in advertising (over 50% of print ads contain human faces), this technique may be quite profitable.

"This technique will revolutionize the field of ad design," predicts author Min Ding.
The technique is eigenface method, which has been widely used for face recognition purposes in other fields, including personal device logons, human-computer interaction, and law enforcement's tracking of suspects. Eigenface method aims to identify each face by a small set of key dimensions that together explain the variations in human faces.

The best book ever
written on how to
write advertising. 
Click on image
The authors used eigenface method to extract and represent facial features in ads with a limited set of eigenface weightings. In an experiment with 989 participants, the authors used real models' faces and real ads with minimal modifications to elicit participants' natural reactions to print ads. Their results show that different faces affect ad effectiveness substantially and people show substantial differences in their facial preferences across product categories.

"An 8% increase in effectiveness could produce a substantial gain for the $600 billion ad industry," says author Li Xiao.

"These methods can substantially increase sales in individual industries," add the authors. "For example, there is a potential for up to $5 billion additional sales for the automotive industry in the U.S. alone."

Ad agencies would use four steps to employ this technique in ad design:
  1. create a single database containing perhaps a thousand or more faces of professional models;
  2. represent each face in the database with a set of eigenface weightings;
  3. measure the facial preferences of target customers in a product category; and
  4. identify the top faces that best match target customers' facial preferences for the specific product category.
These steps can be automated once enough data about characteristics of various product categories and facial preferences have been collected.

I know the average small business person hasn't the money for this type of research, however, knowing how the effect having the right face in your ads is good reason to do some split run advertising tests.  It's actually pretty easy.
  1. Develop one ad - headline, copy, offer, expiration date and so on.  If you've never written advertising professionally, the best book ever on creating effective ads is "Tested Advertising Methods," by Advertising Hall of Fame member, John Caples.  
  2. Use two different model face shots in a split run of the ad.  That's the only difference between the two ads you're testing.  You don't want to add any other elements to the test.
  3. Track response to each ad by the simple technique of coding each ad separately.  You can use different telephone extension numbers.  Ad one could be extension 101, ad two extension 202 (you don't need extensions to do this.) When a caller says, "Extension 101, please," you or whoever answers the phone puts a tick mark in the ad one box.  The same for ad two.
    • Be sure each ad appears the same number of times.
    • Make sure the only difference between the two ads is the face.
  4. At the end of a week or a month, you'll have a clear idea which face is attracting more business, and the winning ad becomes your standard against which you test future ads..
I used this technique to determine which tags on my blogs get the most response.  The winning tag results in nearly three times as many hits, so it works, and I've done something similar for dozens of clients.  Best of all its cheap and easy.
*  *  *  *  *

Story Source: Materials provided by Institute for Operations Research and the Management Sciences. Li Xiao, Min Ding. Just the Faces: Exploring the Effects of Facial Features in Print Advertising. Marketing Science, 2014

No comments:

Post a Comment