Google Inc.

David Earl Barney

Chao Cai

William Patrick Kee

James Edward Stewart

Todd Morris Jackson

Hongxu Cai

Xiaosa Zhao

John Chih Huang

Stefan F Schnabl

Bozhena Bidyuk

Richard Edward Little

Timothy John Wright

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

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 provides systems and methods for enhancing audience measurement data. Offline and online audience measurement data may be compared and correlated to improve the quality of each data and source set. Positive correlations between the offline and online data sets related to a particular event may indicate demographic traits that are likely true, such that outliers may be removed from the set or considered at a reduced weight. Negative correlations may indicate that demographic information within a source set, such as the online measurement data, may be false or suspect.

Systems and methods for enhancing audience measurement data

Growing community of inventors

Mountain View, CA, United States of America

David Earl Barney