Amplitude

Apmplitude, Inc.

Eric Pollmann

Muhammad Bilal Mahmood

Cynthia Rogers

William Robert Pentney

Scott Kramer

Zachery Abe Miranda

Mustafa Paksoy

Systems and methods for data ingestion in real time are described herein. In an embodiment, a server computer receives a message comprising one or more client events from a storage device which publishes the message in response to storing the one or more client events. The server computer stores the one or more client events as raw event strings which are then parsed into parsed event strings. Identity resolution methods are performed on the parsed event strings. Feature groups are then identified in the parsed event strings and used to generate aggregation keys which are used to aggregate the feature groups prior to storing aggregated data in one or more aggregation tables.

Real time system for ingestion, aggregation, and identity association of data from user actions performed on websites or applications

Implementations described herein relate to methods, systems, and computer-readable media for automated generation and use of a machine learning (ML) model to provide recommendations. In some implementations, a method includes receiving a recommendation specification that includes a content type and an outcome identifier, and determining model parameters for a ML model based on the recommendation specification. The method further includes generating a historical user feature matrix (FM), generating a historical content feature matrix (FM), and transforming the historical user FM and the historical content FM into a suitable format for the ML model. The method further includes obtaining a target dataset that includes historical results for the outcome identifier for a plurality of pairs of user identifiers and content items of the content type. The method further includes training the ML model using supervised learning to generate a ranked list of content items for each user identifier.

Automated machine learning to generate recommendations for websites or applications

Systems and methods for computing a causal uplift in performance of an output action for one or more treatment actions in parallel are described herein. In an embodiment, a server computer receives interaction data for a particular period of time which identifies a plurality of users and a plurality of actions that were performed by each user of the plurality of users through a particular graphical user interface during the particular period of time. The server computer uses the interaction data to generate a feature matrix of actions for each user, and a set of confounding variables included to minimize spurious correlations. The feature matrix is then used to train a machine learning system, using data identifying a user's performance or non-performance of each action as inputs and data identifying performance or non-performance of a target output action as the output. A treatment effect is then computed for a treatment action by generating a simulated treatment matrix where all values for the treatment action are set to true, computing an average of outputs from the machine learning system using the simulated treatment matrix, generating a simulated control matrix where all values for the treatment action are set to false, computing an average of outputs from the machine learning system using the simulated control matrix, and computing a difference between the two average outputs.

Machine learning system to predict causal treatment effects of actions performed on websites or applications

Growing community of inventors

Los Altos, CA, United States of America

Eric Pollmann