Male investors are more likely to “freak out” and sell, while women investors are more likely to ride out steep market declines, according to a new study from MIT, which found that panic selling is not only male-dominated, but also predictable.

The study, “When Do Investors Freak Out? Machine Learning Predictions of Panic Selling (,” examined 650,000 brokerage accounts between 2003 to 2015 to chart the frequency, timing and duration of panic sales, which the authors define as a decline of 90% of a household account’s equity assets over the course of one month, of which 50% or more is due to trades.

“We find that a disproportionate number of households make panic sales when there are sharp market downturns, a phenomenon we call ‘freaking out,’” wrote MIT researchers Daniel Elkind, Kathryn Kaminski, Andrew Lo, Kien Wei Siah and Chi Heem Wong.

The worst culprits when it comes to panicky selloffs? “Investors who are male or above the age of 45 or married, or have more dependents, or who self-identify as having excellent investment experience or knowledge tend to freak out with greater frequency,” the authors said.

While “freak outs” are rare events, men engage in such selloffs 1.01% of the time, women 0.91%, the study found.

While much financial services industry research, including a new study from Merrill Lynch Bank of America, finds that many women investors often don’t invest early enough, invest enough or take enough risk, a new finding that they are less prone to emotional trading is an interesting one for financial advisors.

The authors, who developed machine learning models to chart such selloffs, found that panic selling and freak outs are predictable and fundamentally different from other well known behavioral patterns, such as overtrading. The models allowed them to chart when investors might panic sell in the near future, using predictive features, including the demographic characteristics of the investor, their portfolio histories and current and past market conditions.

At the same time, they found that panic selling comes with real costs. “While freaking out does protect investors during a crisis, such investors often wait too long to reinvest, causing them to miss out on significant profits when markets rebound,” the authors said.

“We find that the median investor earns a zero to negative return after he panic sells,” they added. That’s because nearly 31% of the investors who panic sell never return to reinvest in risky assets. However, of those who do, more than 58.5% re-enter the market within half a year, the study found.

Experience does not temper freak outs, the study found. The likelihood of panic sales and freak outs is most pronounced when the investor has self-declared good or excellent investing experience. “Interestingly, those for whom we lack this information, and those who declared themselves to have no investment experience, are less likely to panic sell or freak out,” the authors said.

“Similar to investing experience, we find that investors who describe their investment knowledge as good or excellent panic sell or freak out in higher proportions,” they added.