Google Inc.

Scott S Benson

Abhinay Sharma

Andrew E Silverman

James A Gallagher

Kai Chen

Nicholas Charles Fox

Bhavesh R Mehta

Tomas Lloret Llinares

Markus Mock

Simon Tong

Mark Rose

Joerg Heilig

Dustin S Jackson

Wendy McKennon

Robert Kniaz

Dan Siroker

Adrian Dumitru Corduneanu

Angshuman Guha

Benjamin A Hardy

Gokul Rajaram

Karl Pfleger

An advertiser specifies a conversion-based bid for a conversion event associated with an ad. If a conversion event occurs for the ad, an effective conversion-based bid can be adjusted by a risk premium associated with the ad. An account associated with the advertiser can be debited based upon the adjusted effective conversion-based bid.

Risk premiums for conversion-based online advertisement bidding

Methods, systems, and apparatus, including computer program products, that can include receiving from an advertiser a request for billing based on a first measure of services, determining from quality data related to the advertiser whether the first measure of services can be converted with sufficient confidence to a second measure of services, providing services according to the first measure of services, monitoring stability data indicative of the stability of the relationship between the first measure of services and the second measure of services, and automatically switching from one to another mode of determining a price to be charged the customer for services provided.

Automatically switching between pricing models for services

A system determines a number of times that clients access a group of documents associated with a web site or a group of web sites. At least one document in the group of documents includes at least one advertisement. The system further determines a percentage of client views for an advertiser or an advertising network across the web site or group of web sites based on the determined number of times.

Determining advertising statistics for advertisers and/or advertising networks

A learning model is built on a combination of advertiser, publisher and user data. The learning model can be applied to all advertisers in an advertising system. The learning model provides predicted conversion rates for a given advertisement ('ad') appearing on different publisher networks. A predicted conversion rate represents the probability that a click on a given ad appearing on a given publisher will lead to a conversion. The predicted conversion rates are used to generate a multiplier. The multiplier is used to automatically adjust the advertiser's bid (e.g., maximum cost-per-click (CPC)) for the given ad prior to an auction for the ad. Adjusting the advertiser's bid equalizes a cost-per-conversion among the publishers for the ad.

Automatic adjustment of advertiser bids to equalize cost-per-conversion among publishers for an advertisement

Methods, systems, and apparatus, including computer program products, for determining a probability that a traffic conversion of a content item associated with a content source (e.g., website) will occur based on past traffic patterns for that content source. A traffic conversion defines, for example, minimum traffic interactions of one or more associated user sessions with a content source. The minimum traffic interactions can be based on, for example, the duration of the one or more user sessions on the content source, or a quantity of pages associated with the content source navigated in the one or more associated user sessions.

Determining conversion probability using session metrics

A predicted performance metric of a candidate advertisement in an advertising slot can be received and compared to a baseline predicted performance metric for the candidate advertisement. A target bid associated with the candidate advertisement can be adjusted based upon the comparison, and the adjusted bid can be submitted to an auction for the advertising slot.

Adjusting bids based on predicted performance

Growing community of inventors

Sunnyvale, CA, United States of America

Scott S Benson