Adap.tv, Inc.

Amazon Technologies, Inc.

Lucid Commerce, Inc.

Liang Wei

Brendan Kitts

Dyng Au

Brian M Burdick

Amanda Powter

Garrett James Badeau

Yongbo Zeng

Andrew George Potter

Michael Krishnan

Ishadulta Yadav

Ruofeng Chen

Ethan James Thornburg

Sergey Tolkachov

Davood Shamsi

Sumedh A Kanetkar

Timothy Shawn T Wee

Weifeng Aaron Lin

Sergei Tolkachov

Saurabh Sharma

This paper presents a practical method for measuring the impact of multiple marketing events on sales, including marketing events that are not traditionally trackable. The technique infers which of several competing media events are likely to have caused a given conversion. The method is tested using hold-out sets, and also a live media experiment for determining whether the method can accurately predict television-generated web conversions.

System and method for determining effects of multi-channel media sources on multi-channel conversion events

The present disclosure describes a system that attempts to reconcile diverse goals and re-cast the goals into something that is quantifiable and optimizable. One way to reconcile diverse goals is by converting these 'constraints'—with the huge problems of feasibility—into errors that can be minimized. This disclosure also presents solutions for rate constraints which previously have not been dealt with. The resulting system enables advertisers to dynamically adjust their campaign based on the needs of the moment. Such a system can have advantages in terms of controllability, smoothness, as well as avoiding hard stop conditions that plague the constraint-based approach. In order to achieve this result, solutions are presented for problems of pacing, viewability prediction, and most particularly, error minimization.

Ad serving with multiple goals using constraint error minimization

System and method for attributing multi-channel conversion events and subsequent activity to multi-channel media sources

Systems and methods are disclosed for demographic prediction based on aggregated training data. The predictions are based on auditing aggregated data associated with identified properties of web requests. The audited information is based on a batch of prior web requests that have the same property and have been audited by a measurement company.

Demographic prediction using aggregated labeled data

The present disclosure describes a system that attempts to reconcile diverse goals and re-cast the goals into something that is quantifiable and optimizable. One way to reconcile diverse goals is by converting these 'constraints'&#x2014;with the huge problems of feasibility&#x2014;into errors that can be minimized. This disclosure also presents solutions for rate constraints which previously have not been dealt with. The resulting system enables advertisers to dynamically adjust their campaign based on the needs of the moment. Such a system can have advantages in terms of controllability, smoothness, as well as avoiding hard stop conditions that plague the constraint-based approach. In order to achieve this result, solutions are presented for problems of pacing, viewability prediction, and most particularly, error minimization.

Disclosed are various embodiments for determining an expected number of times that content may be served in conjunction with a user interface. A forecasting model for determining an expected bid requests inventory is generated, wherein a bid request indicates an opportunity to submit a bid to present content in conjunction with a user interface. A bid success rate is determined. An expected impressions inventory is determined based on the expected bid requests inventory and the bid success rate.

Inventory forecasting for bidded ad exchange

Growing community of inventors

Seattle, WA, United States of America

Liang Wei