You are here:
Smart Sampling
Model training is faster with smart sampling. Smart sampling downsizes large datasets to representative samples. Einstein evaluates the data and then selectively reduces the number of rows used to train the model.
Note Einstein Discovery stories are now models. We wish we could snap our fingers to update the
name everywhere, but you can expect to see the previous name in a few places until we replace
it.
Smart sampling impacts only the training data for the model. The data insights for the model are based on the entire dataset.
Smart sampling is automatically applied when smart sampling eligibility criteria are met.
| Dataset Size | Model Algorithm |
|---|---|
| More than 5 million rows |
|
During Model Creation
Smart sampling eligibility is evaluated before the model is created. In General Settings, a notification indicates that smart sampling is applied.
After Model Is Created
In General Settings, a notification shows the reduced row count due to smart sampling.
Did this article solve your issue?
Let us know so we can improve!
