How long does it take to form a habit? 

A team of scientists led by the California Institute of Technology (Caltech) has investigated the process of habit formation by focusing on how long it takes to form two habits: going to the gym and washing hands in healthcare settings. 

By using machine learning to examine these case studies, the experts found that, while it took an average of about six months for gym-goers to form a habit of regularly attending gym, it only took a few weeks for healthcare workers to get into the habit of washing their hands regularly.

“There is no magic number for habit formation,” said study lead author Anastasia Buyalskaya, a former doctoral student at Caltech and currently an assistant professor of marketing at HEC Paris. 

“You may have heard that it takes about 21 days to form a habit, but that estimate was not based on any science,” added senior author Colin Camerer, a professor of Behavioral Economics at Caltech. “Our works supports the idea that the speed of habit formation differs according to the behavior in question and a variety of other factors.”

The scientists used machine learning to analyze large data sets for over 30,000 gymgoers over four years and more than 3,000 hospital workers over 100 shifts. 

“With machine learning, we can observe hundreds of context variables that may be predictive of behavioral execution. You don’t necessarily have to start with a hypothesis about a specific variable, as the machine learning does the work for us to find the relevant ones,” Buyalskaya explained. 

Moreover, while most previous studies were limited to participants reporting their behaviors through surveys, by using machine learning and partnering with 24 Hour Fitness (for the gym research) and a company using radio frequency identification (RFID) technology to monitor hospital hand-washing, scientists were now able to study people’s daily behaviors in their natural environments.

The analysis revealed that certain variables, such as time of day, had no effect on gym habit formation. However there were other factors, like the day of the week, that did make a difference. For example, 69 percent of the gym-goers were more likely to attend the gym on the same days of the week (mostly Mondays or Tuesdays). 

People’s past behavior also played a significant role. For instance, for 76 percent of gym-goers, the amount of time that had passed since their previous gym visit was a major predictor of whether they would go again. The longer that time passed since their last gym visit, the less likely they were to form a habit out of it.

In the case of the hospital hand-washing part of the study, the scientists examined data from workers who were recently required to wear RFID badges recording their hand-washing activity. 

“It is possible that some health workers already had the habit prior to us observing them, however we treat the introduction of the RFID technology as a ‘shock’ and assume that they may need to rebuild their habit from the moment they use the technology,” Buyalskaya explained.

“Overall, we are seeing that machine learning is a powerful tool to study human habits outside the lab,” she concluded.

The study is published in the journal Proceedings of the National Academy of Sciences. 

—

By Andrei Ionescu, Earth.com Staff Writer