The Power of Trading Polarity: Evidence from China Stock Market Crash

TL;DR

This paper introduces 'trading polarity', a high-frequency market sentiment indicator derived from transaction data, which effectively reflects market behavior and can predict market crashes in the China stock market.

Contribution

It develops a novel high-frequency trading polarity measure that captures market sentiment and demonstrates its effectiveness in analyzing market crashes and behavioral shifts.

Findings

Trading polarity reflects market sentiment changes during crashes.

Negative correlation between polarity and returns at market level.

Polarity signals market psychology transitions.

Abstract

The imbalance of buying and selling functions profoundly in the formation of market trends, however, a fine-granularity investigation of the imbalance is still missing. This paper investigates a unique transaction dataset that enables us to inspect the imbalance of buying and selling on the man-times level at high frequency, what we call 'trading polarity', for a large cross-section of stocks from Shenzhen Stock Exchange. The trading polarity measures the market sentiment toward stocks from a view of very essence of trading desire. When using the polarity to examine market crash, we find that trading polarity successfully reflects the changing of market-level behavior in terms of its flipping times, depth, and length. We further investigate the relationship between polarity and return. At market-level, trading polarity is negatively correlated with returns, while at stock-level, this correlation changes according to market conditions, which becomes a good signal of market psychology transition. Also, the significant correlation disclosed by the market polarity and market emotion implies that our presented polarity, which essentially calculated in the context of high-frequency trading data, can real-timely reflect the sentiment of the market. The trading polarity indeed provides a new way to understand and foresee the market behavior.