Patents

We're Inventing Technology that Solves Chronic Customer Data Challenges

Graphic showing three different Amperity patent pages on a dark datawave background

Patents

Stable ID

Patent No. 10,503,696 Maintaining cluster stability over time, so Amperity can reliably serve as your consistent customer ID.

Generating Training Data

Patent No. 10,509,809 Optimized method for sampling and labeling records, with a variety of positive effects.

Multiple Databases

Patent No. 10,599,395 Parameterizing probabilistic clustering to allow for multiple databases.

Transitive Stitching & Fusion

Patent No. 10,853,033 Two methods for combining and merging customer data sources, where n>2.

Clustering of Data Records with Hierarchical Cluster IDs

Patent No. 10,922,337 Clusterings at multiple confidence levels to enable downstream applications with varying precision/recall trade-off needs.

Cluster Conflict Resolution

U.S. Patent No.: 11,003,643 Our identity matching system is not just aiming to detect pairs of records associated with the same identity, but rather to produce coherent identity clusters.

Version Control of Configuration Tree

Patent No. 11,080,043 Enables Amperity to track, analyze and, if necessary, revert changes in data with a single button click.

Validating and Merging Configuration Tables

Patent No. 11,294,666 Allows for rapid cloning and experimentation without impacting the production tenant.

Partitioning Supersized Clusters

Patent No. 11,704,315 Provides the capability to perform cluster analysis and improve the performance in model building & data mining.

Patent No. 11,704,315

Predicting Customer Lifetime Value With Unified Customer Data

Patent No. 11,893,507 Techniques for generating features to train a predictive model to predict a customer lifetime value or churn rate.

See how we put these patents to use

Profile of woman in the center of a web of nodes