Microsoft Technology Licensing, LLC

Sara Smoot Gerrard

Jeffrey Gee

Deepak Kumar

Songtao Guo

Gungor Polatkan

Rupesh Gupta

Rohan Ramanath

Shipeng Yu

Tao Cai

Sahin Cem Geyik

Anish Ramdas Nair

Vijay K Dialani

Cagri Ozcaglar

Daniel Sairom Krishnan Hewlett

Runfang Zhou

Konstantin Salomatin

Alexandre Patry

Onkar Anant Dalal

Jeremy Lwanga

Lingjie Weng

Jiaqi Ge

Wenxiang Chen

William Tang

Tianchen Yu

Sanjay Agarwal

Meilin Yang

Zhongwei Jiang

Tanvi Sudarshan Motwani

Sai Krishna Bollam

In some embodiments, a computer system generates a recommendation for a user of an online service based on user actions that have been performed by the user within a threshold amount of time before the generation of the recommendation. For each user action, the computer system determines an intent classification that identifies an activity of the user and that corresponds to different types of user actions, as well as a preference classification that identifies a target of the activity, and then stores these intent and preference classifications as part of indications of the user actions for use in generating different types of recommendations using different types of recommendation models. Additionally, the computer system may use mini-batches of data from an incoming stream of logged data to train an incremental update to one or more recommendation models.

Recommendations using session relevance and incremental learning

Methods are presented for providing dynamic search filter suggestions that are updated and ranked based on the user filter selections. One method includes detecting a query received in a user interface (UI), calculating, by a search-candidate model, first search results, and calculating, by a suggestions model, first filter suggestions for filter categories to filter responses to the query. The suggestions model is obtained by training a machine-learning algorithm utilizing pairwise learning-to-rank modeling. The first search results and the first filter suggestions are presented in the UI. When a selection in the UI of a filter suggestion is detected, the search-candidate model calculates second search results for the filter categories based on the query and the selected filter suggestion, and the suggestions model calculates second first filter suggestions based on the query and the selected filter suggestion. The second search results and the second filter suggestions are presented in the UI.

Context-aware query suggestions

Techniques for performing prefetching for a ranking service in a microservice architecture are provided. In one technique, in response to receiving a content request, an entity identifier of an entity associated with the content request is determined, a host of a second service that is different than the first service is determined. The first service sends the entity identifier to the host of the second service. The second service retrieves entity feature data that is associated with the entity identifier. The first service identifies a set of content delivery campaigns, identifies the host of the second service, and sends the identity of the set of content delivery campaigns to the host of the second service. The host of the second service determines a ranking of the set of content delivery campaigns, a subset thereof is selected, and data about each selected campaign is transmitted over a computer network.

Entity-sticky-routing ranking feature prefetch in microservice architecture

The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of feature additions and an evaluation metric for assessing the performance of a statistical model. Next, the system automatically builds treatment versions of the statistical model using a set of baseline features for the statistical model and feature combinations generated using the feature additions. The system then uses a hypothesis test and a fixed set of feature values to compare a baseline value of the evaluation metric for a baseline version of the statistical model that is built using the set of baseline features with additional values of the evaluation metric for the treatment versions. Finally, the system outputs a result of the hypothesis test for use in assessing an impact of the feature combinations on a performance of the statistical model.

Feature selection impact analysis for statistical models

Growing community of inventors

Redwood City, CA, United States of America

Sara Smoot Gerrard