A new study into attraction argues that algorithms and interest-based matching systems are not very proficient at predicting attraction in real life.
The study, titled “Is Romantic Desire Predictable? Machine Learning Applied to Initial Romantic Attraction”, was published online last week by the Psychological Science journal.
The research sought to look at whether desire is predictable, by comparing the predictions of an interest and personality-based machine learning algorithm with the actual ratings given by singles after they met with each other.
Prior to the investigation, participants had to fill out questionnaires designed to collect data about over 100 different personality traits and preferences.
They then went on a series of four-minute speed dates with other participants of the study.
After they met in real life, the participants were asked to rate the dates based on three different factors – their level of interest, the interactions they had, and sexual attraction.
The researchers then compared these ratings with the findings of a “cutting-edge machine learning algorithm” which sought to predict which couples would like each other based on the answers to their questionnaire responses.
The results revealed the algorithm could not predict which couples would like each other, but “it was possible to predict the overall tendency for someone to like and to be liked by others”.
Speaking about their findings, lead author and University of Utah psychology professor, Samantha Joel said: “We found we cannot anticipate how much individuals will uniquely desire each other in a speed-dating context with any meaningful level of accuracy.
“I thought that out of more than 100 predictors, we would be able to predict at least some portion of the variance. I didn’t expect we would find zero.
“Attraction for a particular person may be difficult or impossible to predict before two people have actually met.
“A relationship is more than the sum of its parts. There is a shared experience that happens when you meet someone that can’t be predicted beforehand.”
Read more about the study here.