Informatica Corporation

Cloudera, Inc.

Gregorio Convertino

Tianyi Li

Gary W Patterson

Shima Kazerooni

Ranjeet Kumar Tayi

Manish Gupta

Ranjeet Tayi

Chitresh Kakwani

Swati Tomar

Maoyuan Sun

Mark Detweiler

Haley Allen Most

Yi-Hsun Tsai

Michael Tristan Zajonc

Michael John Lee Williams

Wenbo Wang

A system, method and computer-readable medium for data protection simulation and optimization in a computer network, including grouping data stored in data stores in the computer network into groupings according to an architectural or a conceptual attributes, storing, current values of risk metrics for each grouping, each of the metrics corresponding to sensitive domains, receiving a risk reduction goal corresponding to at least one risk metric in the risk metrics, the at least one risk metric corresponding to at least one sensitive domain in the sensitive domains, determining a simulated value of the at least one risk metric for each grouping in the groupings by simulating application of a protection mechanism to sensitive data in each corresponding data store, the sensitive data corresponding to the at least one sensitive domain, and ranking the groupings based on the at least one simulated value of the at least one risk metric for each grouping.

Method, apparatus, and computer-readable medium for data protection simulation and optimization in a computer network

Techniques are disclosed for facilitating the tuning of hyperparameter values during the development of machine learning (ML) models using visual analytics in a data science platform. In an example embodiment, a computer-implemented data science platform is configured to generate, and display to a user, interactive visualizations that dynamically change in response to user interaction. Using the introduced technique, a user can, for example, 1) tune hyperparameters through an iterative process using visual analytics to gain and use insights into how certain hyperparameters affect model performance and convergence, 2) leverage automation and recommendations along this process to optimize the tuning given available resources, 3) collaborate with peers, and 4) view costs associated with executing experiments during the tuning process.

Hyperparameter tuning using visual analytics in a data science platform

A system, method and computer-readable medium for missing data identification, including identifying columns in tables of a database, generating categorical columns of categorical data by transforming data values in the columns into categorical data values, generating a co-occurrence matrix corresponding to a pair of categorical columns in the categorical columns, determining an expected frequency of co-occurrence corresponding to each unique pair of categorical data values based at least in part on a marginal totals corresponding to categorical data values in the co-occurrence matrix, and identifying one or more locations of missing data based at least in part on the count of co-occurrence of each unique pair of categorical data values and the expected frequency of co-occurrence corresponding to each unique pair of categorical data values.

Method, apparatus, and computer-readable medium for missing data identification

An apparatus, computer-readable medium, and computer-implemented method for visualizing relationships between pairs of columns, comprising identifying a relationship classification corresponding to two columns in a plurality of columns based on a data type of each column in the two columns, applying one or more statistical measures to data in the two columns to generate association data quantifying a plurality of relationships between data values in a first column of the two columns and data values in a second column of the two columns, wherein the one or more statistical measures are determined based at least in part on the relationship classification, and transforming the association data into a visualization, wherein the visualization comprises one or more indicators corresponding to one or more relationships in the plurality of relationships and wherein a layout of the visualization is determined based on the relationship classification.

Method, apparatus, and computer-readable medium for visualizing relationships between pairs of columns

A system, method and computer-readable medium for generation of missing data including transmitting indicators corresponding to locations of missing data in columns in tables of a database, each location of missing data corresponding to categorical values of categorical columns and each location of missing data being identified based on an expected count of data values at the corresponding location, receiving a selection of at least one indicator corresponding to at least one location of missing data, the at least one location of missing data corresponding to two or more categorical values of two or more categorical columns in the categorical columns, and generating sets of data records in at least one table in the tables of the database, each set of data records having two or more column values in two or more columns that correspond to the two or more categorical values of the two or more categorical columns.

Method, apparatus, and computer-readable medium for generation of missing data

A system and method are disclosed for providing metric recommendations by a cloud event log analytics system. The log analytics system includes a user interface which allows users to view metric recommendations, view, modify, annotate, delete, or create log metrics. In a first embodiment, centroid vectors are created from metadata associated with user access of log metrics. The centroid vectors are compared to metrics vectors created from log metrics and the results are ranked and provided to users as metric recommendations. In a second embodiment, classification rules are inferred for metric matrix tables containing metadata about log metric usage. Classification rules are assigned to a decision tree used to calculate composite probabilities of interest of log metrics. A recommendation matrix incorporate the composite probabilities of interest to predict the degree of interest an analytics user may have in a log metric for a given role.

Metric recommendations in an event log analytics environment

Growing community of inventors

Sunnyvale, CA, United States of America

Gregorio Convertino