User GuidesAPI ReferenceRelease Notes
Doc HomeHelp CenterLog In
User Guides

Filtering Records in Categorizaton Projects

Filter record categorizations by impact, assignment progress, response categorization, verification status, users, categories and sources.

Filtering to High-Impact Records

  • High-impact records are those records in the categorization project from which the ML model in Tamr learns the most.
  • Each time you update categorization results, Tamr marks new records as being high impact.
    High-impact records comprise the top 1% of all ranked records, excluding verified records.
  • The default sort on the "Categorizations" page is by impact.

To filter to high-impact records:

  1. Navigate to the "Categorizations" tab of a Categorization project.
  2. Select the filter icon on the top left-hand side.
  3. Choose High Impact under the High Impact Records header.

Filtering To Records that Need Verification

To filter to all records that have received input from reviewers but have not been verified by a curator:

  1. Select Filter.
  2. Choose Needs Verification .
  3. Refine this filter further, based on whether records require further verification:
  • To filter to all recors that can be verified to the Top expert suggestion without needing a manual review, turn off Users disagree on categories .
  • To find records that need manual review before verification, turn on Users disagree on categories and turn off Users suggest single category.

Filtering Records by Assignment Progress

To help you track assignment progress, Tamr includes the following filter options:

  • Not Assigned: Find records that were not assigned to any users.
  • Assigned: Find records assigned to at least one user.
  • Everyone responded: Find records that have responses from all assigned users.
  • Some responded: Find records where at least one assigned user has not responded.
  • No one responded: Find records where no assigned users have responded.

To filter records by assignment progress:

  1. Select Filter.
  2. Scroll to ASSIGNMENT PROGRESS.
  3. Chose one or more of Not Assigned, Assigned, Everyone responded, Some responded, and No one responded.

Filtering Records by User Response

To help you filter verified records by user feedback, Tamr includes the following filter options:

  • No User feedback: Find records that have not received user feedback.
  • User feedback: Find records where one or more users have given feedback on the record categorization.
  • Skipped: Find records where one or more users did not know how to respond.
  • Users suggest single category: Find records where all users agreed with the suggested category.
  • Users disagree on categories: Find recordds where users suggested different categories, or where at least one user disagrees with a suggested category.

To filter records by user response:

  1. Select Filter.
  2. Scroll to CATEGORIZATIONS.
  3. Choose one ore more of No User feedback, User feedback, Skipped, Users suggested single category, and Users disagreed on categories.

Filtering Records by Verification Status

To help you track verification status on records in your dataset, Tamr includes the following filter options:

  • Not verified: All records that have been suggested by Tamr or a Reviewer, but not confirmed by a curator or administrator.
  • Verified: A record categorization accepted by a Curator or Administrator. Tamr learns from verified categorizations only.
  • Agrees with Tamr: The verified categorization agrees with Tamr's categorization.
  • Disagrees with Tamr: The verified categorization disagrees with Tamr's categorization.
  • No Tamr suggestion: A categorization has been verified, but Tamr has not yet offered a categorization.

To filter records by verification status:

  1. Select Filter.
  2. Scroll to VERIFICATION.
  3. Choose one or more of Verified, Not verified, Agrees with Tamr, Disagrees with Tamr, and __No Tamr suggestion.

Filtering Record by Confidence

Confidence is a metric you can use to gauge how sure Tamr ML model is in its categorizations for each record. Note that Confidence filters appear only after Tamr has predicted categorizations.

  1. Choose Filter.
  2. Scroll to CONFIDENCE.
  3. Chose one or more of High, Medium, Low, and Custom Range
  4. If you select custom range, a slider appears to help you choose a specific range of confidence based on which to run the filter. When this filter is active, it works together with any other active confidence filters.

Filtering Records by Comments

  1. Select Filter.
  2. Scroll to Comments.
  3. Choose Has Comments.

Filtering Records by an Assignment User

To filter records by an assignment user:

  1. Select Filter.
  2. Scroll to the bottom and choose Select users.
  3. Select a user and choose Update Filter.

Filtering by Category

Filtering by category includes both verified and unverified categories.

To filter records by category:

  1. Select Filter.
  2. Scroll to the bottom and choose Add category.
  3. Select a category and choose Select.

Filtering Records by Source

To filter records by their source:

  1. Select Filter.
  2. Scroll to the bottom and choose Select sources.
  3. Select one or more datasets.