Microsoft Technology Licensing, LLC

Paul Ko

Haipeng Li

Ying Liu

Yu Wang

Shen Huang

Yongzheng Zhang

Chi-Yi Kuan

Ho Joon Park

Mariah E Walton

Shady Elasra

Valter Ernesto Sciarrillo

Fanbin Bu

Swaminath Veeramani

Techniques are provided for predicting talent flow to and/or from a geographical region. In one technique, multiple entity profiles are stored and analyzed to generate training data that is labeled indicating whether a corresponding entity has moved to or moved from a region. A machine-learned prediction model is generated or trained based on the training data. Using the machine-learned prediction model, a prediction is made whether, for each entity corresponding to another entity profile, that entity will move to or move from a particular geographic region. Based on multiple predictions, a number of entities that are predicted to move to or move from the particular geographic region is determined. Talent flow data that is based on the number of entities is presented on a computer display.

Machine learning techniques to predict geographic talent flow

A system and method includes an electronic data storage device to store activity data and profile data of members of a social network including content items individually associated with a content item topic. A processor may obtain the activity data and the profile data, determine an association of the social network topic with at least one of a plurality of social network genres based on the activity data, wherein individual ones of the social network genres are based, at least in part, on a category of the profile data. The processor may store the association of the social network topic with the at one of the plurality of social network genres, and cause a user interface to display information related to the content item topic based, at least in part, on the activity data associated with content items associated with the content item type.

Trending topics on a social network based on member profiles

Generally discussed herein are methods, systems, and apparatuses for retrieving analytics data or other data from a plurality of data sources. In one or more embodiments, a method can include receiving from a client a request to retrieve analytics data, and in response to receiving the request automatically issuing a first query for analytics data from a first data source, the first query in a first format; and automatically issuing a second query for data from a second data source different from the first data source, the second query in a second format different from the first format. The method can include providing the analytics data and the data.

Analytics application program interface

A system and method for content spread visualization includes obtaining activity data related to a content item of the social network, the activity data related to interactions by members of the social network with the content item. A processor generates the visualization based on the activity data, the visualization including indicia arranged in hierarchical branches, the branches extending radially from a primary indicia of the indicia, each of the indicia individually corresponding to one of the activity data and connected to at least one other one of the indicia with a couple based on a relationship between the corresponding ones of the activity data. The processor causes a user interface to display the visualization.

Social network content spread visualization

Growing community of inventors

San Francisco, CA, United States of America

Paul Ko