KMEANS.ELBOW OpenBI

The scatter about the centres for each number of clusters, to choose it.

Group: Many variables at once. OpenBI’s own: DAX has no function of this name.

Syntax

KMEANS.ELBOW ( <table>, <mostK>, <name>, <expression> [, <name>, <expression>] … )

Returns

Table. A row for each k from 1: K, Within SS, Between share, Silhouette (the mean over all rows) and Drop (the share of the remaining scatter that one more cluster takes away).

Remarks

• Pick k where Drop falls away after a large value (the elbow), or where Silhouette is highest.
• Each k is clustered just as KMEANS would cluster it.
• With k = 1, Silhouette and Drop are blank, and Within SS is the whole scatter: (rows − 1) × the number of variables, as the variables are standardised.
• With fewer rows than mostK, the rows stop at one cluster per row.
• A row where any variable is blank is left out. A variable must be a number on every row (text is an error, even text that reads as a number), and one that is the same on every row is an error too.

Compared with DAX

An OpenBI function: DAX has none like it, so a measure or query that uses it works in OpenBI only, not in Power BI or Analysis Services.

Examples

Two is clearly enough

Two clusters take away 98 % of the scatter; a third adds little, and the silhouette falls.

EVALUATE
VAR Shops =
    DATATABLE (
        "Shop", STRING, "Liters", INTEGER, "Visits", INTEGER,
        {
            { "A", 100, 10 }, { "B", 110, 12 }, { "C", 95, 9 },
            { "D", 400, 30 }, { "E", 420, 33 }, { "F", 390, 28 }
        }
    )
RETURN
    KMEANS.ELBOW ( Shops, 4, "Liters", [Liters], "Visits", [Visits] )

How many delivery areas?

EVALUATE
KMEANS.ELBOW ( Places, 5, "Lat", Places[Lat], "Lon", Places[Lon] )

Related functions

KMEANS, KMEANS.CENTERS, PCA.COMPONENTS.

Last updated 3 November 2026 · OpenBI Studio 0.3.74