About Us Contact Us Privacy Policy Terms of Use Accuracy & Fairness Corrections & Clarifications Ethics Code Your Ad Choices
© MEAWW All rights reserved

What makes a successful couple? Scientists have an answer and it’s not your partner's personality traits

The most reliable predictor of a relationship’s success is the partner's belief that the other person is fully committed, suggests analysis
UPDATED JUL 31, 2020
(Getty Images)
(Getty Images)

What predicts how happy people are with their romantic relationships and whether the relationship will work or not? It is a lot more than simply who you are with and instead has a lot to do with the type of relationship you build with a partner and the dynamics you share, according to scientists. The most reliable predictor of a relationship’s success is the partners’ belief that the other person is fully committed, a Western University-led international research team has found. Other important factors in a successful relationship include feeling close to, appreciated by, and sexually satisfied with your partner, says the study, which is a systematic attempt at using machine-learning algorithms to predict people’s relationship satisfaction. The analysis also suggests that relationship satisfaction is not well-explained by one’s partner’s own self-reported characteristics.

“The most robust predictor was perceived partner commitment — how committed you think your partner is to the relationship. I was most surprised by how much partner traits underperformed. Partner traits only predicted 5% of the variance in satisfaction, suggesting that your partner's personality has relatively little to do with how happy you are in your relationship,” Western University psychology professor Dr Samantha Joel told MEA WorldWide (MEAWW). “Satisfaction with romantic relationships has important implications for health, wellbeing and work productivity. But research on predictors of relationship quality is often limited in scope and scale, and carried out separately in individual laboratories,” adds Dr Joel.

Relationship science — an interdisciplinary field spanning psychology, sociology, economics, family studies, and communication — has identified hundreds of variables that purportedly shape romantic relationship quality. The current project, conducted by over 80 scholars from around the world, used machine learning to directly quantify and compare the predictive power of many such variables among 11,196 romantic couples.

The study delved into 43 distinct self-reported datasets on romantic couples. “The team used machine learning, an application of artificial intelligence (AI), to comb through vast combinations of predictors — far more than a single researcher could hope to analyze in a lifetime — to find the most robust and reliable predictors of relationship satisfaction,” says the study published in the Proceedings of the National Academy of Sciences (PNAS). 

The machine-learning study delved into more than 11,000 couples and 43 distinct self-reported datasets on romantic couples (Getty Images)

According to the researchers, this study provides provisional answers to the perennial question: “What predicts how satisfied and committed I will be with my relationship partner?” The results reveal that people’s own judgments about the relationship itself — such as how committed they perceived their partners to be, how appreciative they felt toward their partners, sexual satisfaction, perceived partner satisfaction, and lack of conflict — explained approximately 45% of their current satisfaction.


Individual characteristics, which describe a partner rather than a relationship, explained 21% of their current satisfaction with the relationship. The top five individual characteristics with the strongest predictive power for relationship quality were satisfaction with life, negative affect, depression, attachment avoidance, and attachment anxiety. 

“We used machine learning to try to predict relationship quality among more than 11,000 couples. Own judgments about the relationship predicted up to 45% of the variance in own relationship satisfaction. Own traits predicted up to 21% of the variance in relationship satisfaction. However, traits did not add to the total amount of variance we could predict. The partner's perceptions and traits didn't add anything either. Nothing added to the models beyond own judgments about the relationship,” Dr Joel told MEAWW. She adds, “Relationship-specific variables were about two to three times as predictive as individual differences, which I think would fit many people’s intuitions. But the surprising part is that once you have all the relationship-specific data in hand, the individual differences fade into the background.” 

However, that does not necessarily mean that a person’s choice of a romantic partner is unimportant, say experts. “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,” explains Dr Joel. The current datasets were sampled from Canada, the US, Israel, the Netherlands, Switzerland and New Zealand and the researchers say that they would like to expand to South America, Asia and Africa for future studies.