Microsoft Technology Licensing, LLC

Robert Paul Gorman

David Max Chickering

Ashis Kumar Roy

Manan Sanghi

Sonam Dalal

Izzet Can Envarli

Marc David Diamond

Chika Uchendu

Systems and methods for serving dynamic content (such as advertisements) in response to dynamic content requests are presented. More particularly, systems and methods for serving dynamic content from dynamic content portfolios directed to trending events and/or topics are presented. Upon receiving a dynamic content request, content classifications corresponding to the requested, published content (i.e., the requested content) that included reserved dynamic content space which initiated the dynamic content request are determined. A current trend is identified in a content classification when the dynamic content request volume for the current trend period exceeds the standard/expected dynamic content request volume for the current trend period by at least a threshold amount. When a trend is detected, candidate content portfolios directed to the trending content classification are selected from a set trending content portfolios. A content creative is selected from the candidate content portfolios and returned to the requesting computer user.

Dynamic content delivery for real-time trends

Computer-readable media for determining whether to accept a candidate order from a content provider, or advertiser, to display a particular number of advertisements within a specified time segment are provided. Initially, the content provider may include placement criteria that, among other things, identify a leaf node at which impressions of the advertisement are expected to be rendered. Generally, the leaf node refers to a location within a topic graph that describes inventory that is permissible to allocate to satisfy the candidate order. To perform the determination, the inventory of impressions available for accommodating the candidate order and a log of booked orders scheduled to be placed within the time segment are identified. Linear programs are then utilized to determine whether the estimated inventory that satisfies the placement criteria is available by predictively placing the booked orders at the estimated inventory. If estimated inventory remains available, the candidate order is accepted.

Linear-program formulation for optimizing inventory allocation

Growing community of inventors

Woodinville, WA, United States of America

Robert Paul Gorman