Wearing workout clothes to the gym can be daunting at first. Eventually, you might get into the habit of hitting the gym, taking a Zumba class, or running on a treadmill. According to a new study by social scientists at the California Institute of Technology, it takes an average of about six months to develop a gym routine.
The same study also looked at how long it takes healthcare workers to get into the habit of washing their hands. A few weeks on average.
“There are no magic numbers in habit formation,” says Anastasia Buyalskaya (PhD ’21), now assistant professor of marketing at HEC Paris.Other authors of research published in the journal Proceedings of the National Academy of Sciences, Colin Camerer of Caltech, Robert Kirby Professor of Behavioral Economics, Director and Leadership Chair of the T&C Chen Center for Social and Decision Neuroscience, and researchers at the University of Chicago and the University of Pennsylvania. increase. Xiaomiin Li (MS ’17, PhD ’21) is a former graduate student, postdoctoral researcher, and author at Caltech.
“You may have heard that it takes about 21 days to form a habit, but that estimate is not based on science.” It supports the notion that habit formation rates differ among individuals.”
This study is the first to use machine learning tools to study habit formation. Researchers used machine learning to analyze a large dataset of tens of thousands of people who swipe their badges into the gym or wash their hands during their hospital shifts. For the gym study, the researchers partnered with 24 Hour Fitness, and for the handwashing study, a company that uses radio frequency identification (RFID) technology to monitor handwashing in hospitals. The dataset shows that over four years he tracked over 30,000 gym-goers and over nearly 100 shifts he tracked over 3,000 hospital workers.
“With machine learning, we can observe hundreds of context variables that may predict behavioral execution,” explains Buyalskaya. “You don’t necessarily have to start with a hypothesis about a particular variable, because machine learning does the work of finding relevant variables.”
Machine learning also allows researchers to study people over time in their natural environment. Most previous studies were limited to participants filling out surveys.
The study found that certain variables, such as time of day, did not influence gym habit formation. Other factors played a role, such as my past behavior. For example, for her 76% of gym-goers, the elapsed time since their last gym visit was a significant predictor of whether the person would go to the gym again. In other words, the longer it’s been since you last went to the gym, the less likely it will become a habit. Sixty-nine percent of gym-goers were more likely to go to the gym on the same day of the week, with Monday and Tuesday having the highest attendance.
For the handwashing portion of the study, researchers examined data from healthcare workers given the new requirement to wear RFID badges that record handwashing activity. “Some healthcare workers may have already had habits before we observed them, but we should treat the introduction of RFID technology as a ‘shock’ and rebuild their habits from the moment they use the technology.” I’m assuming there might be a need, ”Buyarskaya says.
“Overall, machine learning has turned out to be a powerful tool for studying human habits outside the laboratory,” says Buyalskaya.
The study, entitled “What Can Machine Learning Tell Us About Habit Formation? Evidence from Exercise and Hygiene,” was published by the Behavior Change Initiative, Caltech’s Ronald & Maxine Linde Institute for Economics and Management Sciences, Funded by Amanohashi & Chrissy Chen. Neuroscience Institute at the California Institute of Technology.
