On the TASKS page, click
the campaign name, Site deduplication in
this example, to open a list of the tasks assigned to you.
ExampleYou need to answer a question to confirm if suspect pairs from a list of childhood education centers are real duplicates. Once you label the records and validate your choice, a Talend Job retrieves the data from the campaign and uses it in the context of matching data on Spark.
Select one task or use the
key to select multiple tasks and click Yes,
NO or NOT SURE to confirm the
relationship between data pairs.
Tasks are tagged with green to show that a decision has been taken on them and your choice is listed in the ARBITRATION column.
- Click VALIDATE CHOICES in the top-right corner of the page to validate the choices you have done on the tasks.
Choices are set, data records are resolved, validated and moved from your list.
What to do next
Use a Talend Job to analyze the data labeled in the Site deduplication campaign and generate a matching model.
For further information, see the Job about generating a matching model from a Grouping campaign from the matching with machine learning scenarios.