Price-Pattern Factors from Intraday Data for Equity Selection

Summary

This research summary proposes stock-selection factors built from daily highs, lows, opens, and average traded prices, arguing that closing-price indicators alone miss information in price movement. It evaluates opening-price spikes, rebounds from intraday lows, and deviations from average price over roughly half-month and one-month windows. The summary reports that the shorter-window factors generally showed stronger selection ability, though results differed after orthogonalization: average-price deviation retained more signal, while some other effects weakened or disappeared.

Regression tests and a top-100 portfolio comparison are reported as supporting incremental value for several factors, with nonlinear terms helping some shorter-window variants. The summary also describes improved portfolio measures and factor weights, but gives limited methodological detail and no full underlying analysis here. Results are historical and may be sensitive to systematic market, liquidity, and policy risks; they do not establish future performance.

Key ideas

• The proposed factors use highs, lows, opens, and average traded prices alongside traditional closing-price inputs.
• The study examines opening spikes, rebounds from lows, and average-price deviation across two lookback horizons.
• Shorter-window factors generally show stronger selection results, but orthogonalization reduces or removes some effects.
• Regression tests and portfolio comparisons suggest incremental value for several factors, including some nonlinear terms.
• The reported historical improvements do not eliminate market, liquidity, or policy risks.

Tags

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