Loading a Saved StockRanker Model into BigQuant DAI

Summary

The post asks how to persist and reload a model produced by the newer BigQuant DAI stock-ranking workflow. It describes reading a model data source, saving it with pandas pickle, then loading it in a custom Python module and writing it back as a data source. The reported attempt fails with a UTF-8 decoding error at the point where serialized data is handled, despite the user’s expectation that the model file can be reused this way.

The author also asks whether DAI workflows can be shared visually and whether the newer interface supports simulation trading or only backtesting. No answer, diagnosis, or verified fix appears in the document, so it offers a troubleshooting scenario rather than a validated method. The file extension and serialization steps may matter: the example writes a pickle while naming the file as CSV, and the later read references a different filename. These mismatches are potential clues, not confirmed causes.

Key ideas

• The post describes exporting a stock-ranking model data source through pandas pickle.
• A custom module attempts to reload the serialized model and write it back as a data source.
• The reported failure is a UTF-8 decoding error while handling the saved model.
• The document asks about visual sharing and simulation support but provides no answers.

Tags

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