Aligning Alpha158 Return Labels with Chinese T+1 Trading

Summary

The post asks why Alpha158 labels use different forward-return horizons in two implementations. It compares a label spanning the close at T+1 to the close at T+3 with a Qlib label spanning T+1 to T+2, then relates those choices to China’s T+1 stock-trading rule. The core issue is whether the label matches the prices and timing available to a strategy that generates a signal after the close.

The author also questions whether a VeighNa backtest would enter at the next open and exit at the following open, which would differ from either close-to-close label. The document offers no answer or empirical comparison, so it teaches a useful framing question rather than resolving the discrepancy. Its practical lesson is to check signal time, executable entry and exit prices, and label horizon together; the appropriate horizon depends on the intended trading and backtesting convention.

Key ideas

• A forward-return label should reflect when a signal is produced and when a position can first be traded.
• The post contrasts two Alpha158 label horizons and asks why they differ.
• China’s T+1 rule constrains same-day resale but does not by itself specify the backtest’s execution prices.
• The post raises a possible mismatch between close-based labels and open-based backtest fills without resolving it.

Tags

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