Yahoo! Inc.

Yahoo Assets LLC

Verizon Media Inc.

Oath Inc.

Yahoo Ad Tech LLC

Yahoo Holdings, Inc.

Jian Yang

Suleyman Cetintas

Xian Wu

Jianchang Mao

John Anthony Tomlin

Mohammad Saberian

Deepak Agarwal

Kuang-chih Lee

Jia Li

Jayavel Shanmugasundaram

Erik Nathan Vee

Sergei Vassilvitskii

Tasos Anastasakos

Ben M Shahshahani

Dongni Chen

Srinath Ravindran

Peiji Chen

Puneet Mohan Sangal

Pengyuan Wang

Long Ji Lin

Pradhan Pattanayak

Amita Gajewar

Sandeep Soni

WenJing Ma

Hong Yao

Oliver Kennedy

Disclosed are systems and methods utilizing neural contextual bandit for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to make item recommendations using latent relations and latent representations, which can improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods use neural network modeling in automatic selection of a number of items for recommendation to a user and using feedback in connection with the recommendation for further training of the model(s).

Neural contextual bandit based computational recommendation method and apparatus

Systems, devices, and methods are disclosed for predicting potential effectiveness of query-triggered internet advertisements received from different web page publishers using a deep learning neural network language model for clustering queries, and for automatically adjusting bids for advertisements by advertisers based on the predicted potential effectiveness. Using query-clusters rather than queries for adjusting bids for advertisements allows for more accurate and more consistent bidding strategy despite of sparsity in historical advertisement performance data, higher return on investments for the advertisers, and higher revenue for the publishers of the advertisements.

System and method for automated bidding using deep neural language models

The technologies described herein serve contextually relevant advertisements under a guaranteed advertisement campaign. A publisher retrieves a guaranteed advertisement campaign related to a webpage available for serving an advertisement, and identifies a set of advertisements relating to the guaranteed advertisement campaign. Advertisement selecting circuitry of the publisher determines whether an advertisement that is contextually relevant to content published at the webpage is present in the set of advertisements. If there is no contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects an alternative advertisement from the set of advertisements that minimizes an under-delivery risk related to the guaranteed advertisement campaign. If there is a contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects the contextually relevant advertisement. Then, the publisher provides the selected advertisement to a client device.

System and method for contextual video advertisement serving in guaranteed display advertising

Systems, devices, and methods are disclosed for determining the quality of traffic received from different web page publishers, and setting a pricing structure for the different traffic based on the determined quality of traffic. Accurately determining the quality of traffic and/or clicks from different publishers allows the network system described herein to offer a fair marketplace with just return on investments (ROI) for advertisers, and offer a robust and accurate traffic quality based pricing model for publishers. Internet based technology, and in particular deep learning techniques available through a neural network, are utilized to determine the pricing structure based on click and/or web page traffic quality measurements generated through the deep learning techniques.

System and method for traffic quality based pricing via deep neural language models

Briefly, embodiments of methods and/or systems of training multiclass convolutional neural networks (CNNs) are disclosed. For one embodiment, as an example, an auxiliary CNN may be utilized to form an ensemble with the collection as a linear combination. The linear combination may be based, at least in part, on boost prediction error encountered during the training process.

Boosted deep convolutional neural networks (CNNs)

An advertisement impression distribution system is programmed to generate an allocation plan for serving a number of advertisement impressions changeable as a result of one or more events, the allocation plan to allocate a first portion of advertisement impressions to satisfy guaranteed demand and a second portion of advertisement impressions to satisfy non-guaranteed demand. The system includes an optimizer programmed to establish a relationship between the first portion of advertisement impressions and the second portion of advertisement impressions, the relationship defining a range of possible proportions of allocation of the first portion of advertisement impressions and the second portion of advertisement impressions; and to impose at least one objective on the relationship including moderating an increase in the number of advertisement impressions available for allocation to the first and second portions, to minimize a cost associated with reducing a quality of the advertisement impressions as their volume increases. The system outputs the allocation plan to an ad serving module to control serving of the advertisement impressions according to the range of possible proportions of allocation between the first and the second portions.

Inventory allocation for advertising with changeable supply landscape

A simulation framework for evaluating revenue that may use a pricing engine that runs at least one pricing algorithm with particular configurations and under particular model market conditions to provide revenue projections.

Pricing engine revenue evaluation

A computer implemented system includes a computer readable storage medium which includes historical demand data for a plurality of advertising inventories, and a processor connected to the computer readable storage medium. The processor is configured for generating a first demand forecast for a first predetermined period of time and a second demand forecast for a second predetermined period of time. The processor is configured for adjusting the first demand forecast by removing an existing demand for each of the plurality of advertising inventories, and for generating a net forecasting demand for each of the plurality of inventories for a third predetermined period of time by combining the second demand forecast and an adjusted first demand forecast. The third predetermined period of time is based on the first and second predetermined periods.

Demand forecasting system and method for online advertisements

An advertisement impression distribution system includes a data processing system operable to generate an allocation plan for serving advertisement impressions. The allocation plan allocates a first portion of advertisement impressions to satisfy guaranteed demand and a second portion of advertisement impressions to satisfy non-guaranteed demand. The data processing system includes an optimizer to establish a relationship between the first portion and the second portion. The relationship defines a range of possible proportions of allocation of the first portion and the second portion. The optimizer generates indicia in accordance with maximizing guaranteed demand fairness or representativeness, maximizing non-guaranteed revenue, and minimizing under-delivery penalties, where the indicia indentifies a determined proportion of the first portion to serve and a determined proportion of the second portion to serve. The data processing system outputs the allocation plan including the indicia to control serving of the advertisement impressions in the determined proportions.

System for allocating advertising inventory in a unified marketplace

An advertisement impression distribution system includes a data processing system operable to generate an allocation plan for serving advertisement impressions. The allocation plan allocates a first portion of advertisement impressions to satisfy guaranteed demand and a second portion of advertisement impressions to satisfy nonguaranteed demand. The data processing system includes an optimizer configured to establish a relationship between the first portion of advertisement impressions and the second portion of advertisement impressions. The relationship defines a range of proportions of allocation of the first portion and the second portion. The optimizer generates a solution maximizing guaranteed demand fairness, non-guaranteed demand revenue, and click value. The solution identifies a determined proportion of the first portion of advertisement impressions to serve and a determined proportion of the second portion of advertisement impressions to serve. The data processing system outputs the allocation plan to control serving of the advertisement impressions.

System for display advertising optimization using click or conversion performance

An improved system and method for pricing of overlapping impression pools of online advertisement impressions for advertising demand is provided. An inventory of online advertisement impressions may be grouped in impression pools according to attributes of the advertisement impressions and advertisers' requests for impressions targeting specific attributes may be received. An optimal price may be computed for each of the impression pools of the inventory of online advertisement impressions using dual values of an optimization program. The values of a dual variable for prices of impression pools on the supply constraints of an objective function for allocating the impression pools may be extracted and iteratively increased on those impression pools which have a dual value greater than the book rate value.

Growing community of inventors

Palo Alto, CA, United States of America

Jian Yang