NEWS23 June 2010

UCLA researchers ‘predict behaviour’ through neuroscience

North America Technology

US— Researchers can use neuroscience to draw information from respondents that they would not be able to describe in a conventional survey – but the technique could also be used to predict consumer behaviour, according to the results of a study by neuroscientists at the University of California, Los Angeles.

The study, which was conducted by UCLA professor of psychology, psychiatry and behavioural sciences Matthew Lieberman (pictured), used brain-scanning techniques to predict whether people would use sunscreen over the course of the week more accurately than the subjects themselves could.

Lieberman assembled a sample of 20 respondents, mostly UCLA students, who do not regularly use sunscreen and asked them whether they intended to use the product over the next week.

At the same time, the participants had their brains scanned using functional magnetic resonance imaging (fMRI) while they were shown public service announcements about sunscreen.

The brain-scanning picked up increased activity in the medial pre-frontal cortex region of the brain, which Lieberman said “strongly indicated” that these people would buy and use sunscreen over the course of the week.

He said: “From this region of the brain, we can predict for about three-quarters of the people whether they will increase their use of sunscreen beyond what they say they will do. If you just go by what people say they will do, you get fewer than half of the people accurately predicted, and using this brain region, we could do significantly better.”

Lieberman and fellow researcher Emily Falk came to this conclusion after they developed a model based on 10 people and then tested it on the next 10. They shuffled the 20 people in different ways to test the model. There are more than 180,000 ways to divide the 20 people into groups, Falk said.

She explained: “We ran a simulation of the 180,000 combinations, developed our model on the first 10 subjects on each of the 180,000 simulations, and tested it on the second 10. We saw a very reliable relationship, where for the vast majority of the 180,000 ways to divide the group up, this one region of the brain, the medial pre-frontal cortex, does a very good job of predicting sunscreen use in the second group.”

The duo said that the model could be very useful to the advertising industry, as well as public health organisations.

Lieberman said: “For advertisers, there may be a lot more that is knowable than is known, and this is a data-driven method for knowing more about how to create persuasive messages.”