Workday, Inc.

H2o.ai Inc.

Prithvi Prabhu

Kevin Scott Beyer

John Glenn Eshleman

James Mulholland

Benjamin Mark Werther

Hans-Frederick Brown

SriSatish Ambati

Mark Landry

Jonathan C McKinney

Arno Candel

Dmitry Larko

A plurality of initial machine learning models are determined based on a plurality of original features. The plurality of initial machine learning models are filtered by selecting a subset of the initial machine learning models as one or more surviving machine learning models. One or more evolved machine learning models are generated. At least one of the evolved machine learning models is based at least in part on one or more new features, which are based at least in part on a transformation of at least one of features of the one or more surviving machine learning models. Corresponding validation scores associated with the one or more evolved machine learning models and corresponding validation scores associated with the one or more surviving machine learning models are compared. At least one of the one or more evolved machine learning models or the one or more surviving machine learning models are selected as one or more new selected surviving machine learning models.

Evolved machine learning models

Systems and methods for interest-driven data visualization systems are illustrated. The system includes a processor and a memory configured to store an interest-driven data visualization application. The application configures the processor to obtain reporting data including a plurality of datasets from an interest-driven business intelligence server system; generate visualization rendering data for the datasets based on associations between visualization metadata and the datasets; and generate visualization image data based on the visualization rendering data. The visualization image data is displayable using and includes visual representations of at least a portion of the reporting data. Pieces of the visualization image data correspond to master and slave visualizations. The slave visualization is related to the master visualization such that input data associated with the master visualization is mapped to the slave visualization and at least one piece of input data associated with the slave visualization is not mapped to the master visualization.

Systems and methods for interest-driven data visualization systems utilizing visualization image data and trellised visualizations

Systems and methods for interest-driven data visualization systems in accordance with embodiments of the invention are illustrated. In one embodiment, an interest-driven data visualization system includes a processor, a memory connected configured to store an interest-driven data visualization application, and metadata storage, wherein the interest-driven data visualization application configures the processor to define reporting data requirements, generate data retrieval job data based on the reporting data requirements, transmit the data retrieval job data, receive aggregate data, create at least one piece of reporting data using the received aggregate data and the reporting data requirements, associate visualization metadata with the reporting data describing the visual appearance of the at least one piece of reporting data, and generate a report using the reporting data requirements and the visualization metadata.

Systems and methods for interest-driven data visualization systems utilized in interest-driven business intelligence systems

Systems and methods for interest-driven data visualization systems in accordance with embodiments of the invention are illustrated. In one embodiment, an interest-driven data visualization system includes a processor and a memory configured to store an interest-driven data visualization application, wherein the interest-driven data visualization application configures the processor to define reporting data requirements, generate data retrieval job data based on the at least one piece of reporting data metadata and the data description metadata, transmit the data retrieval job data to an interest-driven business intelligence server system, receive aggregate data from the interest-driven business intelligence server system, create at least one piece of reporting data using the received aggregate data, the data description metadata, and the reporting data metadata, generate a report using the at least one piece of reporting data, the reporting data requirements, and the visualization metadata, and generate visualization image data based on the generated report.

Growing community of inventors

Sunnyvale, CA, United States of America

Prithvi Prabhu