Show TOC

Function documentationSchedule Model and Forecast Locate this document in the navigation structure

 

You use the Schedule Model and Forecast function to schedule and run jobs for the demand modeling and demand forecasting services provided by Unified Demand Forecast (UDF). You can also use this function to calculate hierarchical priors for specific products in specific locations.

Note Note

Output of the results:

  • The demand models and demand forecasts generated with the Schedule Model and Forecast function are not visible within this function. The function is designed solely for the creation and running of these processes, not the inspection of the output.

  • UDF provides the SAP HANA calculation view sap.is.ddf.udf.viz/CV_POS_TS with generated forecast information to its consuming applications. Note that you can view and manage SAP HANA views in SAP HANA studio.

  • An optional visualization tool for forecast validation is available. For more information, see Validate Forecasts with UDF Launchpad.

End of the note.

Features

Available Services

You can run and schedule the following services with this function:

  • Model By Hierarchy

  • Model By Product Location

  • Forecast by Hierarchy

  • Forecast by Product Location

  • Calculate Hierarchical Priors

Note Note

  • When scheduling a service by hierarchy, you get all products and locations assigned to that hierarchy branch.

  • When scheduling a service by product location, you specify a list of one or more products and one or more locations.

  • For more information about the UDF services and features, see Unified Demand Forecast (UDF).

End of the note.
Holdout Forecasts

To measure forecast accuracy, you can run holdout forecasts. A holdout forecast allows you to compare the UDF forecast against actual sales data. You withhold some of this data from being considered in the modeling and forecasting processes for that period, and then you compare the results to the actual sales data that was withheld.

Holdout tests are best suited for measuring forecast accuracy in a proof-of-concept, pilot, or periodic analysis. Note that holdout forecasts are only available in diagnostic mode and do not affect your production forecast results.

To perform a holdout forecast, you first specify a diag_ID specific to your user. Next, you select a date for the Model End Date field based on the holdout period that you want to compare. Then you model the selected products and locations. As your next step, you enter the Forecast Horizon Start Date for the holdout period and create a forecast. The forecast results are available in the Demand Data Foundation (DDF) system. Once complete, you can export the data into a reporting format of your choice using SAP HANA view CV_POS_TS in package sap.is.ddf.udf.vis.

Example Example

You have 1 year of historical sales data (actuals) in your DDF system: from July 1, 2013 through June 30, 2014. You want to hold out 3 months of your actuals to assess the values that will be forecasted. You create a diag_ID and set the scope for your test, specifying the products and locations. You set the Model To date to March 31, 2014 and the Forecast Horizon Date to April 1, 2014 with a duration of 90 days. Then you model, forecast, and validate the results against the actuals.

End of the example.
Variants

The Schedule Model and Forecast function uses variants to run demand modeling or forecasting processes on the specified set of data (Variant Detail) based on the service type. You can save the variant for later reuse.

Activities

Create Variants

Follow these steps:

  1. Choose Variant Setup.

  2. Enter a name for your new variant.

  3. Enter a service name.

  4. Select the master data system that contains the data that you wish to use.

  5. Choose Variant Detail to specify the data that you wish to process.

  6. Choose Save.

Recommendation Recommendation

  • If you are new to demand modeling and forecasting, start by creating variants that correspond to the lower nodes of your product and location hierarchies to create smaller, shorter, and more manageable jobs.

  • As you become more experienced with these jobs, you can schedule them to recur regularly to run modeling on non-overlapping data sets.

  • Never start by modeling the entire enterprise because this is a long-running job.

End of the recommendation.
Run Jobs Using Variants

Follow these steps:

  1. Choose Process Setup.

  2. Select the variant that you wish to use.

  3. Inspect the Variant Detail settings to make sure this is the data that you wish to process.

  4. Select the criteria that you wish to use (for example, Service Name).

  5. Select an execution mode. For more information about execution modes, see the following section.

  6. Choose Execute.

Note Note

The demand modeling and forecasting processes respect the configuration settings for the selected service name. Those settings are available in the Configure Load Balancing function. For more information, see Configure Load Balancing.

End of the note.
Select Execution Modes

You can run jobs in one of the following execution modes:

  • Start Immediately (foreground)

    Your variant and selection criteria will be used to run the process in the foreground. Use this mode for jobs when you already know how long they will require to run so that they do not exceed the maximum time allowed for a foreground process. A job that exceeds the maximum time might be terminated automatically by the ABAP system. When the mode is done, it displays a success or error message.

  • Schedule Single Execution (background)

    Your variant and selection criteria will be used to schedule a one-time background process to be run at the date and time in the future that you specify. This mode only submits the job and displays the job ID. It does not actually run the job. The system will start the job at the specified time.

  • Schedule Recurring Execution (background)

    Your variant and selection criteria will be used to schedule a recurring background process to be run at the date and time and frequency that you specify. This mode only submits the job and displays the job ID. It does not actually run the job. The system will start the job at the specified time and continue to run it at the specified frequency until you cancel the job.

Recommendation Recommendation

There are restrictions on running demand modeling and demand forecasting while other operations (such as master data imports) are running. You should schedule modeling and forecasting at times when they are least likely to impact these other processes.

End of the recommendation.
Monitor Jobs

You can monitor jobs using the Search for Scheduled Jobs service or transaction SM37. You can see the status of your jobs, cancel jobs, and review the job log for details of their execution and other operations. To find the desired job, use the Job Name and Job ID criteria.

You can review messages generated during demand modeling and forecasting using the Monitor Exceptions function. For more information, see Exception Management.

Investigate Errors

A data error or system error might cause a job to be canceled. To investigate the causes, you can do the following:

  1. Use the Search for Scheduled Jobs function: Select the job that appears as canceled and display the job details.

    For example, you might see a message saying that a SQL error has occurred. You can view this error in the system log (transaction SM21) to investigate further.

  2. Use the Monitor Exceptions function: Search for your job ID and display all messages involved in the job. Take a look at the message long texts to see further details.

    For example, a message might say that forecast decomposition has failed. Here, the most likely cause is a data issue (such as an invalid product location or missing sales data).