When Do Investors Freak Out? Machine Learning Predictions of Panic Selling

Using a novel dataset of 653,455 individual brokerage accounts belonging to 298,556 households, the authors document the frequency, timing, and duration of panicsales, which they 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. The authors find that a disproportionate number of households make panic sales when there are sharp market downturns, a phenomenon they call freaking out. The authors also show that panic selling and freak-outs are predictable and fundamentally different from other well-known behavioral patterns such as overtrading or the disposition effect.