Creating Process Mining Model

From QPR ProcessAnalyzer Wiki
Revision as of 18:44, 28 January 2023 by Ollvihe (talk | contribs)
Jump to navigation Jump to search

This article describes how to create a process mining model in QPR ProcessAnalyzer from CSV files. Data can also be loaded in differences sources using a loading script or an ODBC query.

As an overview, following entities need to be defined for a model:

  1. Datatable for events (eventlog)
  2. Datatable for case attributes (Case attributes are not mandatory, so this is optional.)
  3. Model using these datatables

Here are the step-by-step instructions how to create a model:

  1. Go to the Workspace by clicking the QPR icon in top left.
  2. Create a new project by clicking NEW -> Project. (You can also use an existing project.)
  3. When you are in the target project, click NEW -> Datatable. Define a name for the datatable.
  4. Select the created datatable and click Import.
  5. Select a CSV file, adjust settings for the file and click Start import. (If you don't have any data available, you can try out the sample files).
  6. For the case attributes data, create another new datatable and import data to it. (This is optional, as case attributes are not mandatory to create a model.)
  7. To create the model entity, click NEW -> Model and define a name for the model.
  8. Select the model and click Model Properties.
  9. Open the Cases datasource tab, where to select the cases datatable, and the column that contains the case id.
  10. Open the Events datasource tab, where to select the events datatable and the columns that contain the case id, event type and event timestmap.
  11. Click the Save button to close the dialog.
  12. The model has now been created! You can start analysis by double-clicking the model, which will go to the Process Discovery view.