Microsoft Technology Licensing, LLC

Jorge Banuelos

Neelakantan Sundaresan

Shengyu Fu

Roshanak Zilouchian Moghaddam

Xi Cheng

Ying Zhao

Sebastian Kohlmeier

Krishnan Thazhathekalam

Mahaveer Bhavarlal Kothari

Siyu Yang

Cenzhuo Yao

Kexin Xu

A code completion tool uses machine learning models to more precisely predict the likelihood of a method invocation completing a code fragment that follows one or more method invocations of a same class in a same document during program development. In one aspect, the machine learning model is a n-order Markov chain model that is trained on features that represent characteristics of the context of method invocations of a class in commonly-used programs from a sampled population.

Code completion with machine learning

A machine may be configured to assign digital content campaign treatments to targets of a digital content campaign, at a server. For example, the machine access data pertaining to one or more characteristics of an application. The application is hosted on a client device. The data is stored at a server-side database. The machine determines that the one or more characteristics of the application match one or more targeting criteria associated with a digital content campaign. The digital content campaign includes a plurality of flights of a digital content item. The machine assigns a flight of the plurality of flights of the digital content campaign to the client device. The flight identifies a variant of the digital content item. The machine transmits a communication to the client device via a network. The communication includes a flight identifier associated with the flight.

Running client experiments based on server-side user segment data

Machine learning techniques are used to determine the viability of user data measuring the behavior of a new version of the program when compared with user data that measured the behavior of a previous version of the program. The machine learning techniques utilize statistical techniques in a non-conventional manner to train a system to learn from data obtained from the usage of both a new version of the program and a previous version that accounts for the variability in the user population, time variability of the results of the previous version, and feature coverage between the two test results in order to ensure the suitability of the user data in making estimations or predictions about the performance and reliability of the new version.

Machine learning comparison tools

Growing community of inventors

Kirkland, WA, United States of America

Jorge Banuelos