Microsoft Technology Licensing, LLC

Ye Tu

Shaunak Chatterjee

Chun Lo

Ankan Saha

Yijie Wang

Yiping Yuan

Aastha Nigam

Ying Han

Vrishti Gulati

Yuan Sun

Emilie De Longueau

In an example embodiment, a separate mimicry machine-learned model is trained for each of a plurality of different item types. Each of these models is trained to estimate an effect of mimicry for a user (i.e., a user whose user profile or other information is passed to the corresponding mimicry machine-learned model at prediction-time). The output of these models may be either used on its own to perform various actions, such as modifying a location of a user interface element of a user interface, or may be passed as input to an interaction machine-learned model that is trained to determine a likelihood of a user (i.e., a user whose user profile or other information is passed to the interaction machine-learned model at prediction-time) interacting with a particular item, such as a potential feed item.

Deep embedding learning models with mimicry effect

Techniques for nurturing content creation are provided. In one technique, a particular user is identified. Candidate entities are identified based on one or more attributes of the particular user. For each candidate entity, a feedback sensitivity measure of content creation of the candidate entity is determined. The feedback sensitivity measure is generated based on an amount of feedback, from other users, to content that the candidate entity has created. A score is then generated for the candidate entity based on the measure. A ranking of the candidate entities is determined based on the score of each candidate entity. A subset of the candidate entities is selected based on the ranking. The subset of the candidate entities is transmitted over a computer network to be presented on a computing device of the particular user.

Machine learning techniques to nurture content creation

Systems and methods for engagement mapping based on counterfactual experiments are provided. In example embodiments, a network system receives parameters for one or more counterfactual experiments or tests. Based on the parameters, the network system selects one or more users of a social network platform to subject to the test(s) and selects edges of a social network of each of the one or more users to block. The network system then filters out notifications and feed items from the selected edges of the one or more users. Behavior data of the one or more users based on the filtering out of the notifications and feed items is aggregated, whereby the behavior data indicates engagement of the one or more users on the social networking platform based on the filtering of the notifications and feed items. Recommendations are derived based on the aggregated behavior data and presented to the users.

Network liquidity to engagement mapping

A machine for content-feedback-based machine learning to incent online content creation. The machine accesses a relevance value that identifies a level of relevance of a content item to a user. The content item is created by a content creator. The machine generates, using a machine learning model, a feedback sensitivity score associated with the content creator. The machine generates, based on the relevance value and a product between the feedback sensitivity score and a likelihood of the user providing a feedback signal in relation to the content item, a ranking score for the content item. The machine causes display of the content item, based on the ranking score, in a user interface of a client device associated with the user. An input pertaining to the content item received via the user interface causes improvement of the machine learning model based on updating the one or more feedback features.

Incenting online content creation using machine learning

Growing community of inventors

San Carlos, CA, United States of America

Ye Tu