Palantir Technologies Inc.

Eric Raboin

Arseny Bogomolov

Eric Anderson

Jiawei Marvin Sum

John McKinstry Doyle

Lucas Ray

Glenna Yu

Allen Chang

Joel Ossher

Cooper Bills

Sam Stoll

Denis Rochau

Jack Grossman

Daniel Erenrich

Nathaniel Klein

Ryan Beiermeister

Matthew Levan

Matthew Gerhardt

Kevin Simons

Ryan Smith

James Rosswog

Tim O'Brien

Systems and methods are provided for determining multiple fragments of data to be imported, the multiple fragments of data corresponding to different instances of data obtained from one or more external data sources, the different instances of data each corresponding to duplicate content. The multiple fragments of data that each correspond to different instances of duplicate content can be ingested. The multiple fragments of data can be de-duplicated to determine one or more corresponding object data source records (DSRs). The one or more object DSRs can be imported within a data platform system.

Approaches for managing object data

Display screen or portion thereof with graphical user interface

Display screen or portion thereof with transitional graphical user interface

A computer accesses, from a data repository, profile data of a first entity. The computer determines that a set of information items from the accessed profile data of the first entity are associated with a target activity. The computer determines that the set of information items associated with the target activity includes a subset of information items associated with a second entity. The computer creates or edits, within the data repository, profile data of the second entity based on the subset of information items. The computer provides a digital transmission of at least a portion of the profile data of the second entity.

Building a user profile data repository

Computer implemented systems and methods are disclosed for identifying and categorizing electronic documents through machine learning. In accordance with some embodiments, a seed set of categorized electronic documents may be used to train a document categorizer based on a machine learning algorithm. The trained document categorizer may categorize electronic documents in a large corpus of electronic documents. Performance metrics associated with performance of the trained document categorizer may be tracked, and additional seed sets of categorized electronic documents may be used to improve the performance of document categorizer by retraining the document categorizer on subsequent seed sets. Additional seed sets may and categorizations may be iterated through until a desired document categorization performance is reached.

Systems and methods for identifying and categorizing electronic documents through machine learning

Growing community of inventors

McLean, VA, United States of America

Eric Raboin