Missing Trading Volume Data Can Leave Backtest Factors Empty
Summary
This brief Chinese-language forum post reports a data-quality issue discovered while debugging backtests: some runs returned no results, and inspection showed that certain factors were empty in many cases. The author notes that noticing the missing values through absent predictions helped reveal the problem; if left undetected, empty factor data could affect prediction results.
The post is an operational warning about checking factor inputs and filtered data during backtesting. It does not explain the root cause, quantify the issue, or provide a correction, validation procedure, or example of its effect on returns. It therefore offers a useful reminder to inspect data completeness, but not a full diagnostic method or evidence about any trading strategy.
Key ideas
- Some backtest runs produced no results because one or more factors were empty.
- Inspecting filtered data helped expose the missing factor values.
- Unnoticed empty inputs may affect model predictions.
- The post identifies a data-quality concern but gives no root-cause analysis or fix.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.