High-Frequency Price-Volume Divergence Factors for A-Share Return Prediction

Summary

This research summary describes factors built from intraday snapshot data to measure the relationship between stock prices and trading volume. The reported premise is that price-volume divergence may precede higher returns whether prices are rising or falling, while price-volume agreement may precede weaker returns. The researchers construct six factors and aggregate intraday observations into daily and weekly signals, then apply the approach to a CSI 1000 index-enhancement strategy.

The summary reports that several daily factors had mean information coefficients above 3%; a combined factor exceeded 4%. It gives annualized long-short returns and Sharpe ratios for individual and combined signals, and says neutralization improved the top portfolio’s annualized excess return. For the weekly combined neutralized factor, it reports a 6.27% mean information coefficient, 38.88% annualized long-short return, and 4.08 Sharpe ratio. These figures are summaries of the source report; the underlying PDF is not included here. The available text does not specify sample dates, transaction costs, implementation details, or robustness checks, so the reported results cannot be independently assessed from this excerpt.

Key ideas

• The study uses intraday snapshot prices and volumes to construct six measures of price-volume alignment or divergence.
• The summary reports predictive results at both daily and weekly horizons.
• Combining factors and neutralizing the composite are reported to improve selected performance measures.
• The approach is applied to a CSI 1000 index-enhancement strategy.
• The excerpt omits sample period, costs, and robustness details needed to evaluate the reported performance independently.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.