This page enables you to identify outliers in demand history, and determine ways to correct ‌historical data. It also enables you to review impact of history correction in unit terms resulting from both system and manual correction at a product, customer, and period level.

Before you start

Use the context selectors at the top-right to select a product and customer. Additionally, you can manually enter the required values using the search function.

Use the Customer Filter and Product Filter fields to filter on a specific customer and product.

Select a Time View Settings to focus on a specific timeframe.

Parameter Value
View Years HistoryThis is the number of years history to view. If you enter more than the maximum history available, only the maximum available is shown.
View Period Type

View Period Type: This provides options to view planning periods as either:

  • Fiscal Year: Always shows the current fiscal year as a minimum.
  • Rolling Year: Always shows the current period as a minimum.

History Correction Charts and Tables

This page helps you focus on variances by exception for review and correct as required. The parameters are used to propose history correction through an outlier detection process. The charts let you see how history correction affects your data. 

You can override the parameter values locally, for a product and customer combination, by setting values in the Edit Parameters card:

ParametersValues
Correct From

Specifies the baseline for correction. With From Mean or From Trend, the values are calculated using periodic data starting from the product's effective date and ending with the last effective period:

  • Off: Prevents the application from calculating outliers for correction.
  • From Mean: Calculates outliers based on values greater than x standard deviations from the Mean.
  • From Trend: Calculates outliers based on values greater than x standard deviations from the Trend line.
  • From Trend Seasonal: Calculates outliers based on values greater than x standard deviations from the Trend Seasonal line.
Outlier MagnitudeSpecifies the number of standard deviations from the mean (or standard errors from the trend line) that determine an outlier. A value of 2 highlights data points more than two standard deviations from the mean.
Correct What

Specifies what correction is applied to the outlier's history:

  • Off: Prevents the application from calculating outliers for correction.
  • Spikes: Corrects outliers that are above the upper limit.
  • Dips: Corrects outliers that are below the lower limit.
  • Both: Corrects outliers that are above the upper limit or below the lower limit.
Correct To

Determines the value to which an outlier is corrected:

  • To Limit: Corrects outliers to the upper or lower limit.
  • To Mean: Corrects outliers to the Mean.
  • To Trend: Corrects outliers to the Trend Line.
Period by Period

Determines the value to which an outlier is corrected:

  • To Limit: Corrects outliers to the upper or lower limit.
  • To Mean: Corrects outliers to the Mean.
  • To Trend: Corrects outliers to the Trend Line.

The Effective Parameters display values set in Edit Parameters.

The C–Var Comparison chart shows variances between demand and system-corrected history by significance.

  • C-Var (Mean): Standard Deviation divided by the Mean of pure history value.
  • C-Var (Trend): Standard Error divided by the  Mean of the Trendline.
  • C-Var (Residual): The difference between the Standard Deviation and Predicted values.


Note: A minimum of two years of demand history is required to detect trend seasonality. An alert displays in the Alert card if there is insufficient history.

The History Correction Status card indicates if history correction is possible for the selected product and customer combination.

The spike chart displays the impact of history correction, with a clear view of history before and after correction. 

ParameterValue
Chained History (U)Displays the sum of the Selected History (U) and Inherited History (U) values.
Trend Seasonal (U)Displays the trend line along with it seasonality.
Upper LimitDisplays the Outlier Magnitude value. This controls how many standard deviations from the mean are needed to find an outlier. Values exceeding the upper limit are automatically corrected if "Spikes" or "Both" is specified in the Correct What parameter.
Lower LimitDisplays the Outlier Magnitude value. This controls how many standard deviations from the mean are needed to find an outlier. Any values exceeding the lower limit are automatically corrected if "Dip" or "Both" is specified in the Correct What parameter.
Outlier Range Displays period range of outliers. It's displayed as a rectangle block. 
Corrected History (U)Displays the applied history correction value.

Note: Use legends to view information for any week. Select a legend to show its details in the chart. Hover the cursor over a chart legend to display the legend's values in the chart. Hover the cursor over the data curve to display the data point values.

The history correction table displays the unit volume, percentage value, and final correction impact of automated correction, manual correction, and final correction.

ParameterValue
Chained History (U)Displays the sum of the Selected History (U) and Inherited History (U) values.
Period by PeriodIf Period by Period correction is enabled, you can select the periods to correct.
System Corrected History (U)Displays the applied history correction value.
Manual Correction (U)Displays a value to manually override the System Corrected History (U).
Corrected History (U)Displays the default System Corrected History (U) value unless you've entered a Manual Correction (U) value.
CommentsA text field allowing you to enter comments specific to the product and history correction process step.