Interpreting Adjusted Close Features in BigQuant

Summary

This Chinese-language support note explains why a BigQuant feature such as close_0 may not match the stock’s quoted historical closing price. The example compares a reported feature value of 134.5385 for 600030.SHA on 2021-04-01 with a stated actual close of 23.76. The discrepancy arises because close_0 is provided as a backward-adjusted price by default, rather than as the raw close.

To recover the actual price, the note gives a conversion using the adjustment factor: divide close_0 by adjust_factor_0. This distinction matters when interpreting extracted features, comparing them with exchange prices, or preparing price data for a strategy. The explanation is brief and does not discuss alternative adjustment conventions, corporate-action details, or how adjusted prices should be handled in a particular backtest, so those choices still require context.

Key ideas

• BigQuant's close_0 feature is backward-adjusted by default, so it can differ from the raw historical close.
• The example shows a feature value of 134.5385 versus a stated actual close of 23.76.
• The note says to divide close_0 by adjust_factor_0 to recover the actual price.
• Researchers should identify whether their price features are adjusted before comparing them with quoted prices.

Tags

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