Facial selection technique raises potential buyer numbers

A new facial selection technique for advertisements raises the number of potential buyers by up to 15%, according to a new Marketing Science Study carried out by researchers at the Institute for Operations Research and the Management Sciences (INFORMS), and published in Marketing Science.

The study, titled “Just the Faces: Exploring the Effects of Facial Features in Print Advertising”, was conducted by Min Ding, Smeal Professor of Marketing and Innovation at Smeal College of Business, Pennsylvania State University, and Li Xiao, Assistant Professor of Marketing at Fudan University in China.

Ding and Xiao demonstrated that a technique to screen faces when creating and designing adverts “can transform the current subjective process into a scientifically automated one.”.

Bearing in mind that more than 50% of printed advertisements contain human faces, this new facial selection technique has the potential to dramatically increase sales.

Facial selection technique could revolutionize ad design

Ding predicts that this new technique could revolutionize how ad design is done.

The technique, known as the eigenface method, has been extensively used in other fields for face-recognition purposes, including law enforcement, human-computer interaction, and personal device logons.

The eigenface method “aims to identify each face by a small set of key dimensions that together explain the variations in human faces,” the authors explain.

Xiao and Ding used the eigenface method to extract and represent facial features in advertisements with a specified set of eigenface weightings.

With the help of 989 volunteers, the researchers used the models of real faces and real adverts with minimal modifications to see how the participants reacted to print ads.

Facial features influence people’s reactions to ads

They found that ad effectiveness was significantly altered by different faces; the volunteers displayed a wide range of facial preferences across product categories.

Xiao said:

“An 8% increase in effectiveness could produce a substantial gain for the $600 billion ad industry. These methods can substantially increase sales in individual industries. For example, there is a potential for up to $5 billion additional sales for the automotive industry in the US alone.”

Ad agencies would use four steps

If adopted, advertising agencies would utilize 4 steps to employ this facial selection technique in ad design:

  • Build up a database of possibly 1,000 or more faces of professional models.
  • Define each face in the database with a limited set of eigenface weightings.
  • Gauge specific facial preferences by target customers according to a product category.
  • List the top faces that target customers prefer for the specific product category.

As soon as enough data regarding the characteristics of various product categories and facial preferences have been gathered, these steps can be automated.

In an Abstract in the journal, the authors wrote:

“We also found that the effect of faces interacts with product categories and is mediated by various facial traits such as attractiveness, trustworthiness, and competence. Implications and directions for future research are discussed.”