Can't blame gravity for falling in love, download Clover!

Ok, ok, ok let’s get to the juicy bit: the most reliable predictor of a relationships’ success is a partners’ belief that the other is fully committed, says the research team at Western University, Canada.

But funnily enough, that’s not the only interesting predictor it picked up on!

Other crucial factors included feeling close to, appreciated by and sexually satisfied with your partner, says the study.

This is a HUGE deal! It’s the first systematic attempt at using artificial intelligence to build algorithms to predict human relationship satisfaction! Like how bonkers is it that we can do this now! Let’s move on to the study:

The study:

This massive machine-learning study, conducted by Psychology professor Samantha Joel, Paul Eastwick from University of California, Davis, and a ton of other brilliant minds from across the world, extracted data from more than 11,000 couples!

The data was sourced from Canada, USA, Israel, the Netherlands, Switzerland and New Zealand but researchers want to branch out to South America, Asia and Africa for future studies.

So: What’s the answer to the age-old question: ‘What predicts happiness in a relationship?’

The results!

The 10 strongest relationship-specific predictors are:

According to the study, relationship-specific predictors (like above) made up nearly 50% of what impacts relationship quality.

Individual traits, applicable to the people, not the relationship, explains only a 21% of variance in relationship quality.

Here are the top 10 strongest individual differences predictors:

“Relationships-specific variables were about 2-3x as predictive as individual differences, which I think would fit many people’s intuitions,” Joel said. “But the surprising part is that once you have all the relationship-specific data in hand, the individual differences fade into the background.”

Samantha Joel, Western University

What does this mean?

“Relationship satisfaction is not well-explained by your partner’s own self-reported characteristics”, Joel said; like life satisfaction, depression or agreeableness only explained only 5% of variance in the other person’s satisfaction.

But that doesn’t totally mean the person doesn’t matter.

“Partners may help to shape the relationship-specific processes—such as conflict, intimacy, and perceived partner commitment—that do seem to be so important for relationship maintenance,” Joel added.

What else excites you about machine learning/artificial intelligence?

Hop on to Clover to try our VIRTUAL dating (LIVE VIDEO) feature!

H/T: Western University