Diagnosing Empty Data After Missing-Value Removal in Live Simulation
Summary
This troubleshooting note describes a simulation failure in a single-stock AI ranking strategy: the pipeline reports that no data remains after missing values are removed, even though the strategy completes a backtest. It suggests checking whether the data calculations produce many missing values, since dropping those rows can leave an empty dataset.
The reported resolution was to remove a binding between the training-set code list and live-trading parameters, and the tutorial strategy code was updated accordingly. This points to a configuration mismatch between training and simulated trading as the cause in that case. The note is brief and tied to one strategy template; it does not provide the underlying code or establish that the same fix applies to other pipelines.
Key ideas
- A simulation can fail after missing-value removal if all available rows are dropped.
- The note recommends inspecting calculations and inputs for excessive missing values.
- In the reported case, a training-set code list was linked to live-trading parameters.
- Removing that binding resolved the issue for the referenced strategy template.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.