Use this page to analyze the correlation between demand variability and forecast accuracy.

C-Var and MAPE Analysis

You can set target forecast performance targets for C-VaR ranges.

Parameters

Specify parameters in the Edit Parameters (Global) panel.

ParametersValues
Input for MAPE / AccuracySpecify the default basis for the MAPE / Accuracy analysis calculations from: Demand Plan, Commercial Plan, Consensus Plan, and Stat forecast.
Input for C-VaR

Set which C-VaR measure to use within the C-VaR analysis calculations.

  • C-VaR (Mean): the system-calculated value for the product you selected, calculated based on C-VaR defined as Standard Deviation / Mean of pure history.
  • C-VaR (Trend): the system-calculated value for the product you selected,  calculated based on C-VaR defined as Standard Error / Mean of the Trendline.
  • C-VaR (Residual): the system-calculated value for the product you selected, being the difference in standard deviations of values as compared to the predicted values.

Steps

To change the data that displays on the page, select an option from the context selectors.

To search for an option, enter a numeric reference ID, alphabetic name, or a partial name in the Find... field.

Effective Parameters (Global Forecast Accuracy)

This panel displays the values used for Global Forecast Accuracy.

Parameters

ParametersValues

Forecast Accuracy 


Displays the forecast accuracy measure you selected in the parameters. 
GL Forecast Accuracy Units or RevenueThe target forecast performance targets for C-Var ranges.
GL Forecast Error Basis

The calculation for forecast error is the absolute forecast error divided by the selected divisor. This parameter specifies the divisor used in the calculation.

  • Actuals: this option uses shipment history as the basis for forecast accuracy.
  • Forecast: this option divides the forecast error by the forecast.
  • Minimum Error: this option divides the forecast error by either the history or the forecast (whichever will give the lowest error). This measure can help you to prevent incentivizing behavior that can introduce bias into forecasts.
GL Forecast Accuracy Measure

MAPE forecast accuracy you can measure with the Mean Absolute Percentage Error (MAPE).

Accuracy: specifies forecast accuracy you can measure with Forecast Accuracy (defined as 100% minus MAPE).

GL Lead Time OffestSpecifies the number of planning periods to be used as lead time offset for forecast error calculations. For example, for a forecast made for Week 1, selecting a Lead Time Offset of 2 would begin to measure the forecast made in Week 1 from Week 3.
GL Periods to SumSpecifies the number of planning periods to sum in the calculation of MAPE. From the example above, for a forecast calculated in Week 1, when you select a Lead Time Offset of 2 and Periods to Sum of 3, you would measure the forecast made in Week 1 offset to Week 3, and then summed for Week 3, Week 4 and Week 5.

Forecast Accuracy Target (Bands) Table

Set the first item for C-Var targeting at zero, and build the range from this.


Steps

  • To add a C-Var target band, select Add C-Var Target Band and select Submit. Then modify the values in the table.
  • To delete a band, select the checkbox next to the band and select Delete C-Var Target Bands.

C-Var vs MAPE / Accuracy (%) Chart: All Products

This chart enables you to set accuracy targets. It also displays the analysis of performance. Each product is mapped for its C-VAR vs MAPE Accuracy %.


Steps

To view specific product information alongside the C-VAR and MAPE accuracy percentage scores, hover over any dots on the graph.

Each dot represents an individual product held.

Outliers Table

You can view products, in a table view, plotting the C-Var vs MAPE (both band and target).

This table enables you to identify products where accuracy may be above, or below target. You can investigate these outliers and plan accordingly. You can also filter the table for ease of investigation.