Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

This content has been archived and is no longer being updated.

Links may not function; however, this content may be relevant to outdated versions of the product.

Uploading data for training and testing of the topic detection model

Updated on March 11, 2021

Upload sample records to train the model and to test whether the model assigns the topics correctly.

Before you begin: Prepare a .csv, .xls, or .xlsx file with training and testing data, for example, previous customer messages that have assigned categories.

Tip: To view the structure required for the training and testing data as well as the sample records, in the Source selection wizard step, click Download template.

  1. In the Source selection wizard step, click Choose file.
  2. Select a .csv, .xls, or .xlsx file with sample records for training and testing the model.
    Ensure that the file contains sample records with assigned categories.
  3. Optional: To enable spellchecking, perform the following actions:
    1. Select the Use spell checking check box.
    2. To increase the accuracy of the model by correcting any spelling errors, expand the Select spell checker list, and then select a Spelling Checker Decision Data rule, if available.
    Caution: Enabling spellchecking can significantly increase the model training time, depending on the size of the training sample. Spellchecking also has an impact on real-time performance of the model.
  4. Click Next.
What to do next: Split the uploaded data into a set for training the model and a set for testing the model accuracy. For more information, see Defining the training and testing samples for topic detection.
  • Previous topic Defining a taxonomy for machine learning topic detection
  • Next topic Defining the training and testing samples for topic detection

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us