Microsoft Technology Licensing, LLC

Tatiana Shubin

Sergiy Dubynskiy

Mauktik Gandhi

Michael B Mitchell

Vikram Kakumani

Sandipan Ganguly

Poornima Muthukumar

Dipti A Patil

Brian R Hall

Matthew Spencer Donald Kerr

Shaker Asif Khaleque

Kelly John Forsmann

Sandhya Shahdeo

Steven C Yee

A method and system for analyzing a proximity between a first user population and a second user population includes receiving a request to perform a proximity analysis between the first user population and the second user population, accessing data related to the first user population and the second user population, providing the data related to the first user population and the second user population as input to a machine-learning (ML) model for analyzing the data to determine the proximity between the first user population and the second user population, receiving from the ML model as an output at least one of a composite proximity score between the first user population and the second user population, and providing display data relating to the output to a visualization mechanism for display. The composite proximity score may be calculated based on multiple characteristics and/or comparison metrics.

System and method of determining proximity between different populations

Systems and methods are directed to optimizing survey parameters using machine learning. A network system monitors user activity of a plurality of users with respect to an application and provides a notification to users of the plurality of users that satisfy a trigger condition for providing the notification. The network system obtains feedback corresponding to the notification, whereby the feedback indicates whether each of the users accepted, rejected, or ignored the notification. A machine learning model is then trained using input data obtained from the feedback to optimize on one or more parameters used by the network system in providing a future notification. Based on the machine learning model, the future notification is presented to a further set of users using the one or more optimized parameters.

Reinforcement learning applied to survey parameter optimization

A data processing system implements adaptive telemetry sampling by obtaining first telemetry data from a plurality of telemetry data sources, analyzing the first telemetry data to identify a subset of telemetry data sources for which a reduced sampling rate may be implemented, determining a reduced sampling rate for each event type of the plurality of event types, selecting a subset of the event types for which the reduced sampling rate is to be applied, obtaining second telemetry data from the subset of telemetry data sources at the reduced sampling rate associated with each event type of the subset of event types, analyzing the second telemetry data to determine one or more estimated metric values for one or more metrics, and generating a report comprising the one or more estimated metric values and an estimated total cost saving based on an estimated cost saving associated with each event type.

Adaptive telemetry sampling

Reputation based firewall policy techniques are described, in which, a computer-implemented method may be employed to collect data from a plurality of clients regarding an application attempting to access a network via the clients. The collected data may be exposed to a community of users to obtain feedback on the application which is used to produce a reputation for the application. The reputation may then be provided to the plurality of clients to determine whether to permit the attempt by the application.

Reputation driven firewall

Growing community of inventors

Redmond, WA, United States of America

Tatiana Shubin