Category Property Sets

  1. Select Administration > Application Setup > Forecaster Setup > Category Property Sets.
  2. Click New.
  3. Enter a Name and an optional Description.
  4. Complete the information for: Volume and Traffic Pattern.

Select a Volume Forecast Method:

Best method when you have less than one year of volume data. If you entered 5 days of history to use, the system selects data from 5 of the same type of day in the past 5 weeks. You can select between 3 and 13 like days of data.

In Days of Volume History to Use, select the number of like days for the Forecast Planner to use to forecast volume.

Works if you have more than one year of volume data. If you entered 5 for days of history to use, the system uses a weighted average of like days from the same period of time last year to determine the trend. It applies the trend to the actual values from the forecast week of the prior year to determine the volume forecast.

In Days of Volume History to Use, select the number of like days for the Forecast Planner to use to forecast volume.

Machine Learning is a type of predictive analysis that creates a computer program, or model, by uncovering patterns in data. For example, if you want to predict an estimated selling price of your house, Machine Learning would look at the price of sold houses and their characteristics like location, number of rooms, living area, land area, and so on. From this data, Machine Learning would build a model by finding historical data patterns between the selling price of a house and its characteristics. It would use that model to predict the selling price of a given house.

Machine Learning uses this approach to predict volumes for different drivers, such as sales and items sold, based on characteristics like the day-of-week average.

  1. Enter a weight for each of the listed criteria. The Forecast Planner uses these weights to find the days with the most similar properties. The Total of the weights must equal 100%

    For example, if you entered 4 in Days of Volume History to Use on the Volume tab, the system finds the 4 days that most closely match your criteria, and it uses the weights you enter when it scores each candidate day.

    • Same Day of Week — If you are forecasting for a Monday, the system finds other Mondays.

    • Nearest Day — If you are forecasting for Friday, the system looks at Thursdays. If you are forecasting for Monday, the system looks at Tuesdays.

    • Event — The system finds days with like events.

    • Same Open/Close Time — The system finds days when the store hours are the same as those for the day it is forecasting.

  2. In Days of Pattern History to Use, enter the number of days for the system to use to determine the traffic pattern. The system scores like days and uses the highest scoring days to create the traffic pattern.

Note: You cannot delete a category property set that is assigned to a forecast category.

Select the category property set. Click Delete. Click Yes to confirm.

Forecast categories inherit their property sets from the category in the business structure node that is above them, unless you specify another property set. When you assign category property sets to the business structure, it is best to assign them in order from the top and downward: Root > Sites (Stores) > Departments.

Note: If an alert is triggered at both the department and site levels, only the site level generates the notification.

  1. Select Administration > Application Setup > Forecaster Setup > Category Property Sets.
  2. Click the Assign Category Property Sets tab.
  3. Select the appropriate Forecast Week.
  4. Select the forecast category to which you want to attach a category property set. The system displays the following information:
  5. Category — Pathname of the selected forecast category.
  6. Property Set — The name of the currently assigned category property set, or <None> if none is assigned yet. If the category property set is inherited, the name of the inherited category property set is in parentheses.
  7. Description — Description of the category.
  8. Select a Property Set.
  9. If you do not select a category property set, the forecast category is assigned to Inherited. In this case, Start Date and End Date fields are disabled, and the forecast category takes the same category properties as the level above it.
  10. Enter a Start Date and an End Date for the category property set assignment.
  11. The Start Date must be the first day of a forecast week; for example, Sunday or Beginning Of Time.
  12. The End Date must be the last day of a forecast week or Forever.

  13. Note: You can backdate or enter a date in the future, as long as the effective date range of the assignment is within the effective range of the forecast category.

  14. Select Save.
  15. To select another forecast category and assign a category property set to it, repeat from step 4.