Skip to content

predictadjustedprobability-dmx.md

Latest commit

 

History

History
57 lines (43 loc) · 2.03 KB

predictadjustedprobability-dmx.md

File metadata and controls

57 lines (43 loc) · 2.03 KB
title PredictAdjustedProbability (DMX)
description PredictAdjustedProbability (DMX)
ms.date 02/17/2022
ms.service sql
ms.subservice analysis-services
ms.topic reference
ms.custom dmx

PredictAdjustedProbability (DMX)

[!INCLUDEssas]

Returns the adjusted probability of a specified state.

Syntax

  
PredictAdjustedProbability(<scalar column reference>, [<predicted state>])

Applies To

A scalar column.

Return Type

A scalar value.

Remarks

If the predicted state is omitted, the state that has the highest predictable probability is used, excluding the missing states bucket. To include the missing states bucket, set the <predicted state> to INCLUDE_NULL.

To return the adjusted probability for the missing states, set the <predicted state> to NULL.

The PredictAdjustedProbability function is a [!INCLUDEmsCoName] [!INCLUDEssNoVersion] [!INCLUDEssASnoversion] extension to the [!INCLUDEmsCoName] OLE DB for Data Mining specification.

Examples

The following example uses a natural prediction join to determine if an individual is likely to be a bike buyer based on the TM Decision Tree mining model, and also determines the adjusted probability for the prediction.

SELECT  
  [Bike Buyer],  
  PredictAdjustedProbability([Bike Buyer]) AS [Adjusted Probability]  
From  
  [TM Decision Tree]  
NATURAL PREDICTION JOIN  
(SELECT 28 AS [Age],  
  '2-5 Miles' AS [Commute Distance],  
  'Graduate Degree' AS [Education],  
  0 AS [Number Cars Owned],  
  0 AS [Number Children At Home]) AS t

See Also

Data Mining Extensions (DMX) Function Reference
Functions (DMX)
General Prediction Functions (DMX)