一刻钟效应：加密货币期货中的周期性算法交易与回报可预测性
The Quarter-Hour Effect: Periodic Algorithmic Trading and Return Predictability in Cryptocurrency Futures
浏览论文内容
中文总结 AI 辅助
研究加密货币期货市场周期性波动，利用币安合约交易数据，通过自相关图揭示一刻钟开盘时的序列依赖性，发现其订单不平衡可预测回报，刻画了周期性算法交易及跨频率变化。
中文摘要 AI 辅助
加密货币市场在1小时、5小时和一刻钟标记处呈现出波动性和交易量的周期性爆发。利用六个币安永续合约的交易数据，我们将这些爆发与算法交易联系起来：交易规模的圆润度在爆发期间急剧下降，这是算法参与的行为特征。自相关图（一种时钟相位分辨显示）揭示了常规测量所掩盖的一刻钟开盘时订单流和回报中的序列依赖性。这种开盘活动不仅样本外可预测，而且具有信息价值：其订单不平衡可预测4至12小时的回报，在更精细的标记处较弱。我们的结果刻画了周期性算法交易及其跨频率变化。
英文摘要
Cryptocurrency markets exhibit periodic bursts in volatility and volume at one-minute, five-minute, and quarter-hour marks. Using trade data for six Binance perpetual contracts, we link these bursts to algorithmic participation: trade-size roundness declines sharply during them. The Autocorrelation Map, a clock-phase-resolved display, reveals serial dependence in order flow and returns at quarter-hour openings that conventional measures obscure. Opening returns are predictable out of sample, while opening order imbalance predicts returns over four to twelve hours, with much weaker effects at finer clock-time frequencies. Together, these findings characterize periodic algorithmic trading and its cross-frequency variation.
