User-Defined and Derived Attributes (MERGED_ATTRIBUTES)

The MERGED_ATTRIBUTES tables provides a list of all user-defined and derived attributes that are available in the project. The user-defined attributes include the BY variables and any additional variables that have been imported into the project. The derived attributes that are also added in this table come from the OUTSTAT, OUTSUM, and OUTMODELINFO tables.

In addition, the demand classification attributes are included in MERGED_ATTRIBUTES.

Resolving Duplicate Variable Names in MERGED_ATTRIBUTES

Some variables are in multiple tables with duplicate names. When they are added to MERGED_ATTRIBUTES, they are renamed to distinguish them. The following table shows how the original variable name matches to the renamed variable in MERGED_ATTRIBUTES.

Original Variable Name	Original Table	Variable Name in MERGED_ATTRIBUTES
_MODEL_	OUTMODELINFO	OUTMODELINFO_MODEL
_MODEL_	OUTSTAT	OUTSTAT_MODEL
_STATUS_	OUTMODELINFO	OUTMODELINFO_STATUS
_STATUS_	OUTSUM	OUTSUM_STATUS
_STATUS	Demand classification attributes	DC_ATTRIBUTES__STATUS_
N	OUTSTAT	OUTSTAT_N
N	OUTSUM	OUTSUM_N
NOBS	OUTSTAT	OUTSTAT_NOBS
NOBS	OUTSUM	OUTSUM_NOBS
MODEL	OUTMODELINFO	OUTMODELINFO__MODEL_
MODEL	OUTSTAT	OUTSTAT__MODEL_

Note: If an out-of-sample regionthe number of time periods before the end of the data that are removed when fitting models. After model selection, forecasts are generated in the out-of-sample region and then compared to the actual data to determine accuracy. is set for the project, additional variables are added to MERGED_ATTRIBUTES to enable you to create filtersa set of specified criteria that are applied to data in order to identify the subset of data for a subsequent operation, such as continued processing. based on the out-of-sample statistics of fit. These attributes appear in the Forecast Viewer as Forecast attributes (Out-of-sample). In the table, the attribute names are prepended with OUTSTAT_FORECAST_. See Using an Out-of-Sample Region for more information.

Demand Classification Attributes

SAS Visual Forecasting analyzes patterns in the time seriesan aggregation of transactional data into specified time intervals and sorted according to unique combinations of the default attributes (BY variables) for a project and classifies these patterns to generate attributes. Demand classification attributes represent characteristics of times series such as intermittence, volume, volatility, and seasonalitya regular change in time series data values that occurs at the same point in each time cycle.. See Demand Classification for complete descriptions of these demand patterns.

Note: For external forecasta numerical prediction of a future value for a specified time period for each unique combination of BY variable values projects, demand classification attributes are listed on the Data tab. However, they are not available for the project in the Filters pane for the Time Series Viewer, Forecast Viewer, or Overrides.

Changing any of the Project Settings for this project can lead to errors.

Label	Variable Name	Description
Volume Volatility Class	_VOLUME_VOLATILITY_CLASS	values that identify different ranges of volume and volatility in the time series. Time series that exhibit high volatility are difficult to forecast accurately and might need special attention to identify any inputs that might generate better results. In the Filters pane, you can select from the following patterns that have been detected in the time series. HIGH_VOLUME_HIGH_VOLATILITY LOW_VOLUME_HIGH_VOLATILITY HIGH_VOLUME_LOW_VOLATILITY LOW_VOLUME_LOW_VOLATILITY RETIRED SHORT INTERMITTENT OTHER
Demand Class	_DEMAND_CLASS	A specific set of classifications based on patterns detected in the time series. These classifications are used to segment the time series in the Demand Classification pipeline. See Demand Classification for more information. Select from the following possible values for the _DEMAND_CLASS attribute. Some of these values might not show in the Filters pane if no time series meet the criteria for that attribute. SHORT Time series with a short record of historical data. This could be a new series with only a few observations. The Naive (Moving Average) Forecasting pipeline is selected for this segment. Moving average is already selected as the naive model type. LOW_VOLUME Time series with low volumes. The Naive Forecasting pipeline is selected for this segment. Seasonal random walk is already selected as the naive model type. INSEASON_INTERMITTENT Short time span series with intermittent patterns. The Regression Forecasting pipeline is selected for this segment. INSEASON_NON_INTERMITTENT Short time span series without intermittent patterns. The Regression Forecasting pipeline is selected for this segment. YEAR_ROUND_INTERMITTENT Long time span series with intermittent patterns. The Auto-forecasting model (Intermittent) pipeline is selected for this segment. Only the IDM model is selected for inclusion. YEAR_ROUND_SEASONAL Long time span series with seasonal patterns. The Seasonal Forecasting pipeline is selected for this segment. YEAR_ROUND_NON_SEASONAL Long time span series without seasonal patterns. The Non-seasonal Forecasting pipeline is selected for this segment. YEAR_ROUND_SEASONAL_INTERMITTENT Long time span series with seasonal and intermittent patterns. The Temporal Aggregation Forecasting pipeline is selected for this segment. Moving average is already selected as the naive model type. YEAR_ROUND_OTHER Long time span series with no patterns that can be classified. The Naive (Moving Average) Forecasting pipeline is selected for this segment. Moving average is already selected as the naive model type. OTHER Time series that do not span long time periods and cannot be classified. The Naive (Moving Average) Forecasting pipeline is selected for this segment. Moving average is already selected as the naive model type. RETIRED Time series that are retired or are no longer active. The Retired Series model is selected for this segment.
Seasonal	_SEASONAL	indicates whether the time series is seasonal. Seasonality is determined by a significance probability of 0.01 or less. In the Filters pane, select Y to show only seasonal series or N to show only series that are not seasonal. Select ND for time series for which seasonal patterns could not be determined.
Intermittent	_INTERMITTENT	indicates whether the time series is intermittent. In the Filters pane, select Y to show series that indicate intermittent patterns or N for series that are not intermittent.
Seasonal Intermittent	_SEASONAL_INTERMITTENT	indicates whether the time series is seasonal intermittent. In the Filters pane, select Y to show series that are both seasonal and intermittent series or N for series that are not a combination of seasonal and intermittent. Select ND for time series for which seasonal intermittent patterns could not be determined.
Retired	_RETIRED	indicates whether the time series is retired. In the Filters pane, select Y to show only series that are retired or N for series that are not retired.
Short	_SHORT	indicates whether the time series is a short period. In the Filters pane, select Y for series that indicate a short pattern or N for series that are not short.
Volume	_VOLUME	the volume of the time series. In the Filters pane, select from LOW , MEDIUM , or HIGH .
Volatility	_VOLATILITY	the volatility of the time series. Usually, series with high volatility are harder to automatically forecast than series with low volatility. In the Filters pane, select either LOW or HIGH .
Demand Span	_DEMAND_SPAN	the length of the time series. This is used to determine whether time series are year round or seasonal prior to further classification for the Demand Classification pipeline. In the Filters pane, select any of the following options. YEAR_ROUND for time series with values that spread throughout the year, like sales for basic goods INSEASON for time series that occur only during certain seasons, such as sales for seasonal goods ND the length of the demand patterns could not be determined
Trailing Zero Length	_TRAILING_ZERO_LENGTH	the number of trailing zeros in the time series. In the Filters pane, select from any detected numeric range.
Maximum Cycle Length	_MAXIMAL_CYCLE_LENGTH	the maximum value of the demand cycle lengths detected from the time series. In the Filters pane, select from the values detected from time series.
Volume Measure	_VOLUME_MEASURE	the actual volume measurement value of the time series. In the Filters pane, select from a numeric range, starting with the lowest detected volume measure in the time series to the highest.
Demand Interval	_DEMAND_INTERVAL_MEASURE	the median value of the demand intervals. This value is used for detecting if the series is intermittent or not. Select from the numeric values detected in the time series. Note: This attribute is listed in the Filters pane as `Demand Interval Measure` .
Volatility Measure	_VOLATILITY_MEASURE	the actual volatility measurement value of the time series. In the Filters pane, select from a numeric range, starting with the lowest detected volatility measure in the time series to the highest.
Status	_STATUS_	a value that indicates whether analysis for each time series was successful. You can select one or more of the following conditions. 0 - Analysis was successful 3000 - Accumulation failed 4000 - Missing value interpretation failed 6000 - Series is all missing 9000 - Descriptive statistics could not be computed

In time series projects, you can use these attributes to create filters in all of the viewers. See Viewers for Time Series in Your Project for more information. The filters are listed in the Filters pane by the label.

Last updated: March 16, 2026