Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Time-series modeling

Availability information

Time series modeling is not currently available for DataRobot Self Service users.

Time-series modeling is a recommended practice for data science problems where conditions may change over time. With this method, the validation set is made up of observations from a time window outside of (and more recent than) the time window used for model training. Time-aware modeling can make predictions on a single row, or, with its core time series functionality, can extract patterns from recent history and forecast multiple events into the future.

Topic Describes...
What is time-based modeling? The basic modeling process and provides a recommended reading path.
Workflow overview The workflow for creating a time series project.
Date/time partitioning The underlying structure that supports time aware modeling.
Time series modeling Building time series models and making predictions with them.
Multiseries modeling Modeling with datasets that contain multiple time series.
Segmented modeling Grouping series into segments, creating multiple projects for each segment, and producing a single combined model for the data.
Nowcasting Making predictions for the present and very near future (very short-range forecasting).
Enable external prediction comparison Comparing model predictions built outside of DataRobot against DataRobot predictions.
Time series modeling data The time series modeling dataset and restoring pruned features.
Time series reference Deep-dive reference material for DataRobot time series modeling.

Updated April 22, 2022
Back to top