• AmpIQ
  • Amp360
  • AmpID
  • DataGrid
  • Amperity A-Z

AmpID

AI-powered customer identity management.

What is AmpID?

AI-powered identity management that correctly identifies your customers.

How ID resolution works

Learn more about how Stitch correctly identifies your customers.

Tools for ID Resolution

1. Add semantic tags

Apply semantic tags to your data in feeds or custom domain tables.

2. Run Stitch

Assign a unique ID to each unique individual that is discovered in your data.

3. Review Stitch results

Review every connection. See how customer identities were resolved.

Apply Semantic Tags

Add semantic tags

Apply to all fields that contain PII.

Apply to feeds

A feed will infer tags for fields that contain PII.

Apply to domain tables

Reshape data with Spark SQL, then apply tags fields that contain PII.

Stitch QA

What should you look at during Stitch QA?

Anomalies in output

It’s important to look for anomalies in Stitch output.

Blocking keys

A blocking key defines combinations of characters for blocking strategies.

Customer keys

Customer keys represent unique IDs in your source data.

Foreign keys

Foreign keys act as primary keys and are used for deterministic matching.

Overclustering

False positives occur when records are incorrectly added to clusters.

Problem nicknames

Given name variations can prevent accurate clustering.

Record pairs & scores

Low-scoring record pairs should be investigated to validate accuracy.

Semantic tags

Consistent application of tags across sources builds better customer profiles.

Underclustering

False negatives that occur when distinct records are incorrectly split.

Values to blocklist

Identify values to add to your bad-values and 360 values blocklists.

Customize Stitch Results

Bad-values blocklist

Exclude values that do not improve the quality of your customer profiles.

Customer 360 blocklist

Include values for ID resolution; exclude them from your Customer 360.

Nicknames

Variations in given names are associated with the same individual.

Configure Stitch

Blocking strategy

Blocking strategies determine how records are linked during ID resolution.

Case-sensitive FKs

Identify foreign keys that contain case-sensitive values.

Empty tables

Empty tables can be present with CCPA and GDPR workflows.

Ignored email patterns

Email address with certain patterns will be ignored by Stitch.

Matching strategy

Tell Stitch how to apply the results of your blocking strategies.

Matching thresholds

All records with scores that are equal to / better than this value cluster together.

Preprocessing profiles

Configure preprocessing profiles to support a variety of edge cases.

Recorded history

Amperity stores 30 days of changes to clusters and primary keys by default.

Stitch reports

Configure Stitch reports to include or exclude specific Amperity IDs.

Supersized clusters

A threshold at which matching records do not identify unique individuals.

Trivial duplicates

The threshold at which nearly-identical records collapse into one record.