MicroStrategy ONE
List of available aggregation functions
The following is a list of the available aggregation functions. The corresponding index (used by the ScoreAgg, ConfidenceAgg and Outputs function parameters) appears next to each function.
-
Average (14): Use 'Avg' if the predictive metric generates a confidence or percentage.
-
Count (13): Use 'Count' to return the number of scores in a set of data.
-
Geometric Mean (34): Use 'GeoMean' whenever several quantities are multiplied to produce a product. While Average answers the question, "if all the quantities had the same value, what would that value have to be to achieve the same total?", Geometric Mean answers the question, "If all the quantities had the same value, what would that value have to be to achieve the same product?"
-
Maximum (16): Use 'Max' to return the highest result from a set of data.
-
Median (30): Use 'Median' to return the middle of a set of data, where half the scores are above the median and half are below the median.
-
Minimum (15): Use 'Min' to return the lowest result from a set of data.
-
Mode (31): Use 'Mode' if the predictive metric generates a numeric classifier, like a cluster/segment number. The mode is the most frequently occurring score in a set of data.
-
Product (29): Use 'Product' to return the result of multiplying a set of scores together.
-
Standard Deviation (32): Use 'Stdev' to describe how "spread out" a set of scores is. Standard Deviation is the square root of Variance.
-
Sum (12): Use 'Sum' if the predictive metric generates a score that is a zero or a one or if the predictive metric generates a "linear" output, usually from a regression predictor.
-
Variance (33): Use 'Var' to describe how "spread out" a set of scores are. Variance is the square of Standard Deviation.
-
None (0): Use 'None' for models with outputs that cannot or should not be aggregated.