Google Inc.

Stefan F Schnabl

Chao Cai

Jon Vaver

Bozhena Bidyuk

William Patrick Kee

Richard Edward Little

John Chih Huang

David Earl Barney

James Edward Stewart

Wenjie Jiang

John Huang

Ruixue Fan

Todd Morris Jackson

John Chih Chang Huang

Stephanie Sapp

Hongxu Cai

Xiaosa Zhao

Arjun Satyapal

Systems, methods, and computer-readable storage media for attribution modeling using withheld or near impression data are provided. One method involves determining, for a first content item impression, withheld or near impressions for a competing content item within a content auction. The method further involves identifying a first set of paths including a sequence of events that includes an interaction with the first content item impression. The method further involves identifying a second set of paths, each including the sequence of events with the competing content item impression replacing the first content item impression. The method compares conversion metrics for the first and second paths to determine attribution credit for the first content item impression.

Attribution modeling using withheld or near impressions

Methods, systems, and apparatus including computer programs encoded on computer-readable storage media are provided for evaluating an attribution model, based on simulated activity streams. Parameters are specified that describe how users behave in the absence and presence of advertising, and parameters that regulate advertising in a simulation. A first set of simulated activity streams is generated with advertising turned on, observational metrics associated with the first set of streams are determined, and an attribution model is applied to determine a first fraction of incremental conversions associated with one or more advertising channels. Further sets of simulated activity streams are generated, each with a single advertising channel turned off, observational metrics associated with the further sets of streams are determined, and a second fraction of incremental conversions is determined for each advertising channel. The first and second fractions of incremental conversions are compared to evaluate the attribution model.

Evaluating attribution models based on simulated activity streams

Methods, systems, and apparatus including computer programs encoded on computer-readable storage media are provided for evaluating attribution models and comparing estimates produced by the attribution models with causal measurements from controlled experiments. An attribution model is identified for use in determining an estimate of an effectiveness of a campaign. An experiment is identified including experiment data that reflects implementation of a change in an experiment environment including identifying a measure of effectiveness of the change within a predetermined confidence level. The estimate is evaluated as compared to the identified measure of effectiveness. A determination is made that the attribution model is an effective measure of the change for the campaign, based at least in part on the evaluating.

Evaluating attribution models

Systems and methods for creating a data-driven attribution model are described. A processor identifies visits to a website. The processor identifies a path for each visitor identifier associated with the visits. The processor determines, for each path type associated with the identified paths, a path-type conversion probability based on a number of visits corresponding to the path type that resulted in a conversion. The processor calculates, for each of a plurality of the path types, a counterfactual gain for each event based on a conversion probability of the given path type and a conversion probability of a path type that does not include the event for which the counterfactual gain is calculated. The processor determines, for each event, an attribution credit based on the calculated counterfactual gain of the event. The processor then stores the attribution credits of each of the events.

Methods and systems for creating a data-driven attribution model for assigning attribution credit to a plurality of events

Methods and systems for providing for display attribution data associated with one or more events are disclosed. Processor identifies channels from paths including events corresponding to position data identifying a position along the path at which the event was performed. Processor determines attribution credits assigned to each event included in the paths corresponding to the channel. Processor determines a number of attribution credits assigned to the channel. Processor identifies, from the paths, a plurality of event-position pairs. Each event-position pair corresponds to events that correspond to a respective channel and are performed at a respective position of the plurality of paths corresponding to the event-position pair. Processor determines, for each identified event-position pair, a weighting based on an aggregate of the attribution credits assigned to the events to which the event-position pair corresponds. Processor provides, for display, a visual object including an indicator to display the determined weightings.

Methods and systems for displaying attribution credit data based on parameters

Systems and methods for measuring conversion probabilities of a path types for an attribution model includes, identifying by a processor, paths taken by visitors to visit a website. The paths correspond to a sequence of events that cause a visitor to visit the website. The processor can identify as paths, for each path, subpaths corresponding to each visit to the website. The processor computes a total path count for each path type. The processor identifies, for each path type, a conversion path count indicating a number of paths taken by visitors that resulted in a conversion at the website. The processor calculates, for each path type, a probability of conversion and then provides the calculated probability of conversion for a given path type for an attribution model used in assigning attribution credit to events of a path.

Methods and systems for measuring conversion probabilities of paths for an attribution model

Systems and methods for selecting content for display at a device includes, identifying by a processor, a visitor identifier associated with a device on which to display content. The processor can identify a path associated with the visitor identifier. The path corresponding to a sequence of one or more events through which the visitor identifier has visited the website. The processor can identify a conversion probability of the identified path. The conversion probability of the identified path indicates a likelihood that the visitor identifier will convert at the website. The conversion probability of the identified path is a ratio of a number of conversions at the website to a number of visits to the website over a given time period. The processor can select content for display. The content selected based on the identified conversion probability of the identified path.

Methods and systems for selecting content for display based on conversion probabilities of paths

The present disclosure includes systems and techniques relating to identifying value marketing activities. In some implementations, an apparatus, systems, or methods can include receiving conversion path information including data relating to user interactions with a content item associated with a marketing activity, determining a first attribution credit by applying a first attribution model to the received information, and a second attribution credit by applying a second attribution model to the received information, determining an attribution contrast ratio based on the first and second attribution credit, identifying an opportunity based on the determined attribution contrast ratio, and presenting a recommendation for the marketing activity based on the identified opportunity.

Growing community of inventors

San Francisco, CA, United States of America

Stefan F Schnabl