Spectral Volume Models: Universal High-Frequency Periodicities in Intraday Trading Activities

Abstract

We develop spectral volume models to systematically estimate, explain, and exploit the high-frequency periodicity in intraday trading activities using Fourier analysis. The framework consistently recovers periodicities at specific frequencies in three steps, despite their low signal-to-noise ratios. This reveals important and universal high-frequency periodicities across 2,573 stocks in the United States (US) and Chinese markets over three full years. The dominant frequencies are 10-second, 15-second, 20-second, 30-second, 1-minute, and 5-minute in the US and 30-second, 1-minute, 2.5-minute, 5-minute, and 10-minute in China. They explain a significant fraction of the total variance of intraday volumes. Through three different perspectives, we provide evidence that this phenomenon likely reflects the behaviors of trading algorithms with repeated and regular trading instructions. Finally, we demonstrate that uncovering such high-frequency periodicities improves intraday volume predictions and generates return risk premiums. Long-short portfolios constructed based on a periodicity factor yield monthly alphas of up to 0.9% in the US and 5% in China.

Keywords: Trading volume; Spectral analysis; Periodicity; Algorithmic trading; Risk premium.

JEL Classification: C32, C55, G12, G14