A recent study by social scientists at the California Institute of Technology (Caltech) has found that the length of time it takes to establish a habit varies greatly depending on the behavior in question. The study, which used machine learning to analyze large sets of data from tens of thousands of people, found that on average, it takes about six months to establish a gym habit, while healthcare workers form a hand-washing habit in just a few weeks.
The study, which was published in the journal Proceedings of the National Academy of Sciences and funded by the Behavior Change for Good Initiative, the Ronald and Maxine Linde Institute of Economics and Management Sciences at Caltech, and the Tianqiao and Chrissy Chen Institute for Neuroscience at Caltech, is the first to use machine learning to study habit formation. The researchers employed machine learning to analyze large data sets of gym-goers who swiped their badges to enter the gym and healthcare workers who were given RFID badges that recorded their hand-washing activity.
Anastasia Buyalskaya, lead author of the study and assistant professor of marketing at HEC Paris, said that 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.”
The study found that certain variables had no effect on gym habit formation, such as time of day. Other factors, such as one’s past behavior, did come into play. For instance, for 76 percent of gym-goers, the amount of time that had passed since a previous gym visit was an important predictor of whether the person would go again. In other words, the longer it had been since a gym-goer last went to the gym, the less likely they were to make a habit of it. Sixty-nine percent of the gym-goers were more likely to go to the gym on the same days of the week, with Monday and Tuesday being the most well-attended.
For the hand-washing part of the study, the researchers found that it took an average of a few weeks for healthcare workers to get in the habit of washing their hands regularly. Buyalskaya said that although it is possible that some healthcare workers already had the habit prior to being monitored, the introduction of the RFID technology was treated as a “shock,” and the assumption was made that they may need to rebuild their habit from the moment they started using the technology.
Colin Camerer, one of the study’s authors and Robert Kirby Professor of Behavioral Economics and director and leadership chair of the T&C Chen Center for Social and Decision Neuroscience at Caltech, said that there is no magic number for habit formation and that the speed of habit formation differs according to the behavior in question and a variety of other factors.
The study emphasized the power of machine learning in researching human behavior outside laboratory conditions. Machine learning allowed the researchers to study people over time in their natural environments, something that was not possible with most previous studies, which were limited to participants filling out surveys.
Overall, the study provides valuable insights into how habits are formed and could have implications for a wide range of fields, from marketing and advertising to healthcare and education. By understanding the factors that influence habit formation, organizations can design interventions that are more likely to succeed in encouraging people to adopt new habits.
