Removing Delisted Stocks from AI Strategy Training and Validation
Summary
This brief guide explains how to exclude delisted stocks from both the training and validation data flows in a visual AI stock-selection strategy. It instructs users to insert a shared “remove delisted stocks” module before the missing-data handling module in each flow, so the model processes a more consistent universe across training and validation.
The document offers procedural guidance only; it provides no backtest results, comparison, or details on how the module identifies delisted securities. It is marked as an older version and points readers toward a newer guide. The method is specific to the described platform workflow, and the note does not discuss survivorship bias, the timing of delisting information, or the effect of filtering on model performance.
Key ideas
- Add a delisted-stock filter before missing-data processing in the training flow.
- Apply the same filter in the validation flow for consistency.
- The guide is an older platform-specific note and supplies no performance evidence.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.