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

Abstract

Using a novel dataset of 653,455 individual brokerage accounts belonging to 298,556 households, we document the frequency, timing, and duration of panic sales, which we 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.' We 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. Highlights• We define a heuristic to identify investors who sell off a substantial proportion of their risky assets abruptly, or panic sell. We find that investors panic sell more often when there are large market movements.• Panic selling is suboptimal if executed in an improving market, but it is beneficial as a stop-loss mechanism in rapidly deteriorating markets.• Artificial intelligence techniques can identify individuals at risk of panic selling in the near future when given the demographic characteristics of the investor, their portfolio histories, and current and past market conditions.

The underlying coherent behavior in intraday dynamic market equilibrium

“…Their model shows that investors can be either overconfident or panicked based on price momentum. The strongest positive correlation in behavior occurs during price reversals when many investors are more likely to sell their risky assets in a panic" (Elkind et al, 2022). Currently, have applied the differential equation to examine the existence of intraday dynamic market equilibrium using tick-by-tick high-frequency data from the Shanghai Securities Exchange in the Chinese stock markets in which intraday momentum, reversal and interaction exist widely.…”

“…Their model shows that investors can be either overconfident or panicked based on price momentum. The strongest positive correlation in behavior occurs during price reversals when many investors are more likely to sell their risky assets in a panic” (Elkind et al ., 2022). Currently, Shi et al .…”

Shed old baggage and invest wisely. A bibliometric and thematic analysis of disposition effect and investment

“…Recent research focuses on areas like machine learning in understanding the disposition effect. For example, Elkind et al (2022) applied machine-learning predictions to panic selling to state that panic selling differs from the disposition effect as the former can be predicted using machine learning.…”