Configure data exploration¶
On a deployment's Settings > Data exploration tab, prediction row storage is enabled, activating the Data exploration tab. Here, you can export a deployment's stored training data, prediction data, and actuals to compute and monitor custom business or performance metrics on the Custom metrics tab or outside DataRobot.
On a deployment's Data Exploration Settings page, configure the Prediction Data Collection setting:
| Field | Description |
|---|---|
| Enable prediction row storage | Enables prediction data storage, a setting required to store and export a deployment's prediction data for use in custom metrics. This setting is enabled by default. |
Next steps¶
After enabling prediction row storage, export data for analysis or use it to build custom metrics.
- Data exploration: Export your deployment's stored training data, prediction data, and actuals for analysis.
- Custom metrics: Use the exported data to compute and monitor custom business or performance metrics.
- Set up custom metrics monitoring: Define "at risk" and "failing" thresholds for the custom metrics you create from this exported data.