Indicates that a variable is missing a high percentage of values, which can lower the quality of your insights or 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.
Actions to Consider
- For numeric variables, consider imputing missing values by configuring statistical imputation on a numeric variable. To learn more, see Replace Missing Numerical Values.
- Add the missing values in data prep and refresh your training data.
- Add the missing values in the source system and refresh your training data.
Detection Methodology
Einstein Discovery raises this data alert for a variable when a threshold percentage of the values are unspecified.