| FIRE feature selection |
Learn about the benefits of Feature Impact Rank Ensembling (FIRE)—a method of advanced feature selection that uses a median rank aggregation of feature impacts across several models created during a run of Autopilot. |
| Time series to images |
Generate advanced features used for high frequency data use cases. |
| Use case dependencies |
Use an application that allows you to view dependency graphs for DataRobot Use Cases. |
| Acoustic data with Visual AI |
Generate image features in addition to aggregate numeric features for high frequency data sources. |
| Prediction intervals |
Learn about the various methods to generate prediction intervals for any DataRobot model. The methods are rooted in conformal inference (also known as conformal prediction). This accelerator focuses on prediction interval generation for regression targets. |
| Robust feature selection |
This accelerator introduces an approach to select robust features, use multiple seeds for cross validation, add dummy features to compute the median permutation importance, and then select the most robust dummy features. |
| Use case explorer |
Provides a template for a project management dashboard that collects all the key artifacts in a Use Case and displays them on a timeline. |