A new model to predict when people are most likely to try different products has been developed by a team of scientists at UCL including Turing Faculty Fellow, Professor Brad Love and dunnhumby, a customer science company.
The research, published today in the inaugural issue of Nature Human Behaviour, could help to direct public health interventions aimed at encouraging healthier choices.
The team analysed anonymous purchase data from over 280,000 shoppers who regularly bought products in six categories: beers, breads, coffees, toilet papers, washing detergents and yogurts. Individual shoppers were represented only by anonymous dataset numbers with no personal or identifiable information.
“We developed a model to predict when somebody is ready to try a new product, such as switching from one brand to another,” says Professor Brad Love, senior author of the study, who is based at UCL Psychology and began a Fellowship at The Alan Turing Institute in October 2016. “Our model shows that the more people purchase a product, the more likely they are to continue to do so, until they reset the cycle by exploring a new product. To test our theory in the real world, we sent coupons to thousands of people and used the model to predict who would use them. The model worked – people who had recently switched brands were twice as likely to use the coupons to try a new product.”
Previous studies using monetary rewards have found the opposite pattern; the longer someone has chosen to receive a reward of known value, the more likely they are to choose an uncertain reward on the next try. The new research shows that this is different with subjective rewards, where choices drive preferences rather than preferences driving choices.
“One way to see it is that someone who drives a BMW becomes a BMW person rather than ‘BMW people’ buying BMWs,” explains Professor Love. “People might like to reflect on why they like certain products and be wary of buying the same brand out of habit. If you’re trying to start healthier habits in the New Year, my advice would be to stick with something consistently at the start so you’ll be more likely to keep it up in future.”
The study also found that shopping behaviour was consistent across the different product categories. For example, people who were more likely to ‘explore’ and try new beers were also more likely to try new washing detergents.
At The Alan Turing Institute, Professor Love continues his research in understanding consumer behaviour using large datasets, and is interested in exploring how deep learning networks relate to brain function. Additionally, he is interested in pursuing a machine learning collaboration in which lessons from neural computation could be used to improve the performance of these models on a variety of tasks, including object recognition.
You can read the full paper online here: http://www.nature.com/articles/s41562-016-0017
For media enquiries and the full UCL press release, contact Harry Dayantis in the UCL press office, T: +44(0)20 3108 3844, M: +44(0)7747 565056, E: firstname.lastname@example.org