Resolving BigQuant ErrorReturnCode_84 by Reducing Model and Data Load
Summary
The note describes two ways to address an ErrorReturnCode_84 encountered when running a BigQuant strategy with a StockRanker module. One option is to increase the AI Studio compute configuration. The other is to reduce the dataset and lower the model’s leaf-node count and minimum samples per leaf, reducing resource demand during training.
The author reports that the example ran successfully in their environment and presents the two changes as alternatives. No error trace, resource diagnosis, benchmark, or comparison between the fixes is provided, so the note does not establish the precise cause or which adjustment is best for a particular workload. The suggestions are practical troubleshooting leads rather than a documented diagnosis; users may need to check their own data size, model settings, and available compute resources.
Key ideas
- Increasing AI Studio compute capacity may resolve the reported run failure.
- Reducing dataset size can lower the workload placed on StockRanker.
- Lowering leaf-node count and minimum samples per leaf are suggested model adjustments.
- The note offers no error trace or evidence identifying the failure’s exact cause.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.