Microsoft Technology Licensing, LLC

David Pardoe

Jinyun Yan

Yin Zhang

Kun Liu

Parvez Ahammad

Yuan Gao

Ryan M Rogers

Kancheng Cao

Yang Zhao

Jing Wang

Manoj Rameshchandra Thakur

Haishan Liu

Jan Schellenberger

Rahul Tandra

Man Chun D Leung

Ryan T Tecco

Vinay Praneeth Boda

Shawn F Ren

Chongzhe Li

Bing Liu

Yajun Wang

Lijun Peng

Embodiments of the disclosed technologies receive first event data associated with a first party application, receive second event data representing a click, in the first party application, on a link to a third party application, receive third event data from the third party application, convert the third event data to a label, map a compressed format of the labeled third event data to the first event data and the second event data to create multi-party attribution data, group multiple instances of the multi-party attribution data into a batch, add noise to the compressed format of the labeled third event data in the batch, and send the noisy batch to a second computing device. A debiasing algorithm can be applied to the noisy batch. The debiased noisy batch can be used to train at least one machine learning model.

On-device privatization of multi-party attribution data

The present disclosure describes various embodiments of methods, systems, and machine-readable mediums which may be used in conjunction with a campaign for distributing content to users of the social network. Among other things, embodiments of the present disclosure provide a number of advantages over conventional systems for content distribution, including a simplified targeting process and increased reach (i.e. distribution) for content providers among users of a social network, as well as improving the utilization of an inventory of content and higher and more efficient engagement with such content by users of the social network.

Audience expansion for online social network content

Techniques for controlling item frequency using machine learning are provides. In one technique, two prediction models are trained: one based on interaction history of multiple content items by multiple entities and the other based on predicted interaction rates and an impression count for each of multiple content items. In response to a request, a particular entity associated with the request is identified and multiple candidate content items are identified. For each identified candidate content item, the first prediction model is used to determine a predicted interaction rate, an impression count of the candidate content item is determined with respect to the particular entity, the second prediction model is used to generate an adjustment based on the impression count, and an adjusted entity interaction rate is generated based on the predicted interaction rate and the adjustment. A particular candidate content item is selected based on the generated adjusted entity interaction rates.

Controlling item frequency using a machine-learned model

Techniques for controlling resource usage in a computing environment are provided. In one technique, a target resource usage for a particular point in time is determined for a content delivery campaign. Determining, for the content delivery campaign, a current resource usage for the particular point in time. Also, a bandwidth associated with the target resource usage at the particular point in time is determined. Based on a difference between the current resource usage and one or more boundaries of the bandwidth, a throttling factor is calculated. Based on the throttling factor, a probability of the content delivery campaign participating in a content item selection event is determined.

Resource usage control system

Techniques for accounting for position-specific differences in user interaction while conducting content item selection events are provided. In one technique, a position-specific factor is determined. The position-specific factor may be based on a ratio of an observed interaction and a predicted interaction. Different positions in a content item feed or on a web page may be associated with different position-specific factors. Eventually, multiple content items are identified for presentation on a screen of a computing device. The content items include a first content item for which a predicted interaction rate is calculated and a second content item for which no predicted interaction rate is calculated. An order of the content items is determined based on the position-specific factor. For example, the predicted interaction rate of the first content item is modified based on the position-specific factor. The content items are presented on the screen based on the order.

Position-aware corrections in content item selection events

Growing community of inventors

Mountain View, CA, United States of America

David Pardoe