The Quarter-Hour Effect: Periodic Algorithmic Trading and Return Predictability in Cryptocurrency Futures

2026-07-10

AI Summary

This study investigates the periodic fluctuations and surges in trading volume observed in cryptocurrency markets at hourly, 5-minute, and 15-minute intervals, whose origins and implications for return predictability remain unclear. Leveraging high-frequency trade data from six Binance perpetual futures contracts, the authors employ measures of order size roundness, order flow imbalance, and phase-resolved autocorrelation analyses to characterize algorithmic trading behavior around these clock-time nodes. The work uncovers a novel “fifteen-minute effect”: order imbalances precisely aligned with 15-minute marks exhibit significant predictive power for returns over horizons of 4 to 12 hours. Notably, this predictability diminishes at finer temporal granularities, suggesting that coarser periodic signals carry stronger informational content about future price movements.

Abstract

Cryptocurrency markets exhibit periodic bursts in volatility and volume at one-, five-, and quarter-hour marks. Using trade data for six Binance perpetual contracts, we associate these bursts with algorithmic trading: trade-size roundness declines sharply within them, a behavioral signature of algorithmic participation. The Autocorrelation Map, a clock-phase-resolved display, reveals serial dependence in order flow and returns at the quarter-hour openings that conventional measures conceal. This opening activity is not only predictable out of sample but also informative: its order imbalance forecasts four-to-twelve-hour returns, weaker at finer marks. Our results characterize periodic algorithmic trading and its cross-frequency variation.

Problem

• Quarter-Hour Effect
• Algorithmic Trading
• Return Predictability
• Cryptocurrency Futures
• Order Flow

Innovation

• Quarter-Hour Effect
• algorithmic trading
• Autocorrelation Map
• order imbalance
• return predictability