Table of Contents

Article

Adaptive Decision Manager data mart tables

Adaptive Decision Manager (ADM) data mart tables contain data snapshots of all the models in ADM. You can use this data mart for ADM reporting and monitoring in the Reports section of the Analytics Center portal. When you need to customize ADM model reports to serve your business needs, you need to understand all the properties that are part of the PR_DATA_DM_ADMMART_MDL_FACT and PR_DATA_DM_ADMMART_PRED_FACT tables.

Properties in the PR_DATA_DM_ADMMART_MDL_FACT table

Properties with the py prefix are defined on the Data-Decision-ADM-ModelSnapshot class.

PropertyDescription
pxCommitDateTimeNot used in ADM reports.
pxSaveDateTimeNot used in ADM reports.
pyModelIDUnique identifier for each ADM model.
pzInsKeyNot used in ADM reports.
pxInsNameNot used in ADM reports.
pxObjClassNot used in ADM reports.
pxApplicationName of the application.
pyIssueDefault model identifier that defines the model context in your application. For more information, see Model context.
pyGroupDefault model identifier that defines the model context in your application.
pyNameDefault model identifier. When the context of the models is different from the default hierarchy, this property contains the context values in the JSON format.
pyChannelDefault model identifier that defines the model context in your application.
pyDirectionDefault model identifier that defines the model context in your application.
pyTreatmentDefault model identifier that defines the model context in your application.
pyConfigurationNameName of the Adaptive Model rule to which the model is associated.
pyAppliesToClassThe Applies To class of the Adaptive Model rule to which the model is associated.
pyActivePredictorsNumber of active predictors for each model.
pyTotalPredictorsNumber of all predictors for each model.
pyNegativesNumber of negative responses for each model.
pyPositivesNumber of positive responses for each model.
pyResponseCountNumber of all responses for each model.
pyRelativeNegativesDifference between the number of negative responses for each model and the number of negative responses for each model in the last snapshot.
pyRelativePositivesDifference between the number of positive responses for each model and the number of negative responses for each model in the last snapshot.
pyRelativeResponseCountDifference between the number of all responses for each model and the number of all responses for each model in the last snapshot.
pySnapshotTimeTime when the snapshot was taken.
pySuccessRateNot used in ADM reports.
pyPerformancePerformance of each ADM model.
pyMemoryNot used in ADM reports.
pyPerformanceThresholdNot used in ADM reports.
pyCorrelationThresholdNot used in ADM reports.
pyExtensionNot used in ADM reports.

Properties in the PR_DATA_DM_ADMMART_PRED_FACT table

Properties with the py prefix are defined on the Data-Decision-ADM-PredictorBinningSnapshot class.

PropertyDescription
pxCommitDateTimeNot used in ADM reports.
pxSaveDateTimeNot used in ADM reports.
pyModelIDUnique identifier for each ADM model.
pxObjClassNot used in ADM reports.
pzInsKeyNot used in ADM reports.
pxInsNameNot used in ADM reports.
pyPredictorNameName of a predictor.
pyContentsOverall range of the predictor.
pyPerformancePerformance of the predictor.
pyPositivesNumber of positive responses for the predictor per model.
pyNegativesNumber of negative responses for the predictor per model
pyTypeType of the predictor (numeric or symbolic).
pyTotalBinsNumber of bins for the predictor per model.
pyResponseCountNumber of responses for the predictor per model.
pyRelativePositivesDifference between the number of positive responses for the predictor and the number of positive responses for the predictor in the last snapshot.
pyRelativeNegativesDifference between the number of negative responses for the predictor and the number of negative responses for the predictor in the last snapshot.
pyRelativeResponseCountDifference between the number of all responses for the predictor and the number of all responses for the predictor in the last snapshot.
pyBinNegativesNumber of negative responses for the predictor per model in the bin.
pyBinPositivesNumber of positive responses for the predictor per model in the bin.
pyBinType

Type of the bin:

  • Equibehavior - A bin type for the so called normal bins. Bin ranges have the same values within one bin.
  • Missing - A bin type for empty values.
  • Residual - A bin type for symbols that did not fit in any of the normal bins because, for example, they occur relatively infrequently. This bin type applies to symbolic fields.
pyBinNegativesPercentagePercentage of negative responses in the bin out of all responses for the predictor.
pyBinPositivesPercentagePercentage of positive responses in the bin out of all responses for the predictor.
pyBinSymbolActual range of the bin.
pyBinLowerBoundLower bound of the bin. This property applies to numeric predictors.
pyBinUpperBoundUpper bound of the bin. This property applies to numeric predictors.
pyRelativeBinPositivesDifference between the number of positive responses for the predictor in the bin that is measured per model and the number of positive responses for the predictor in the bin from the last snapshot.
pyRelativeBinNegativesDifference between the number of negative responses for the predictor in the bin that is measured per model and the number of negative responses for the predictor in the bin from the last snapshot.
pyBinResponseCountTotal number of responses for the predictor in the bin that is measured per model.
pyRelativeBinResponseCountDifference between the number of all responses for the predictor in the bin that is measured per model and the number of all responses for the predictor in the bin from the last snapshot.
pyBinResponseCountPercentagePercentage of responses falling under a particular bin for a predictor that is measured per model.
pySnapShotTimeTime when the snapshot was taken.
pyBinIndexIndex assigned to a predictor bin entry. For example, when a model contains the AGE predictor that has 10 bins, then we have 10 entries in the table and the pyBinIndex for each entry is : 1, 2, 3, 4, 5, 6, 7, 8, 9, 10.
pyLiftBehavior in the predictor bin divided by the overall behavior.
pyZRatioNumber of standard deviations that their behavior in the predictor bin differs from the overall behavior.
pyEntryTypeIndication whether it is an active or inactive predictor. Active predictors are the ones that are used by the model.
pyExtensionNot used in ADM reports.
pyGroupIndex

Not used in ADM reports.

This property cannot be compared between different model versions (updates) because this is just an index.

pyCorrelationPredictorNot used in ADM reports.

Published October 3, 2017 — Updated August 23, 2018

Related Content

Have a question? Get answers now.

Visit the Pega Support Community to ask questions, engage in discussions, and help others.