Indicates that, for a numerical value, Einstein Discovery devised an alternative set of buckets (grouping of data points based on ranges).
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.
Actions to Consider
Bucketing is key to making your insights interpretable. Try using the recommended buckets in your model to see whether they improve the interpretability of your insights.
Detection Methodology
Einstein Discovery uses Kernel Clustering Density, an unsupervised machine learning algorithm, to analyze numerical data. The alert indicates that the clustering algorithm determined an alternate set of bucket ranges (not the default bucketing by decile or quartile).