Google Inc.

Chao Cai

Cameron Michael Tangney

Eric W Ewald

Sagnik Nandy

Japjit Tulsi

Ming Lei

Robert A Walker

William Patrick Kee

Zhimin He

Bozhena Bidyuk

Richard Edward Little

David Earl Barney

Sissie Ling-Ie Hsiao

Stefan F Schnabl

John Chih Huang

Hui Sok Moon

Lik Mui

Matthew Robert Jones

Sissie Ling-le Hsiao

Timothy John Wright

Ashok Babu Amara

John Chih Chang Huang

Todd Morris Jackson

Simon Wang

David Allan White

James Edward Stewart

Karl Pfleger

Reuven Lax

Paul Nicolas Muret

Jesse Savage

Yuan Zhuge

Liren Chen

Niranjan Heddese Sitaram Shastry

Douglas VanderMolen

Hongxu Cai

Paul Liu

Lili Liu

Sissie Hsiao

Nagaraju Pothineni

Xiuduan Fang

Xiaosa Zhao

Sissie Ling-Le Hsiao

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing conversion path performance measures and reports. In one aspect, user interaction data are obtained, were the user interaction data specify user interactions for a plurality of conversions. User interactions that are associated with each conversion are selected from the user interaction data, where the associated user interactions for each conversion are user interactions with a converting user during the conversion cycle for the conversion. Using the user interaction data for the selected user interactions, a quantity of user interactions that are associated with each conversion and occurred during the conversion cycle for the conversion are determined. In turn, conversion path performance measures are computed and reports specifying the conversion path performance measures are generated.

Conversion path performance measures and reports

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for dynamically generating and configuring pre-aggregated datasets optimized for responding to particular types of data requests made against a large sub-optimal multidimensional dataset are disclosed. A dynamic aggregator monitors the query types and response latencies associated with queries made against the large multidimensional dataset. The dynamic aggregator defines pre-aggregated datasets based on the types of queries received from users and calculates a respective benefit score for each pre-aggregated dataset. The benefit score of each pre-aggregated dataset can be based on the recorded latencies and query count for the pre-aggregated dataset. The dynamic aggregator can decide whether to generate and/or maintain particular pre-aggregated datasets based on the current values of the benefit scores associated with the particular pre-aggregated datasets.

Dynamically generating pre-aggregated datasets

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 creating rules for assigning attribution credit across events, includes, identifying, by a processor, conversions at a website. The processor identifies path types associated with the conversions. Each path type identifies events and a index position indicating an event's relative position. The processor identifies a subset of the identified path types to be rewritten according to a path rewriting policy. The processor then rewrites the identified subset of the identified path types as rewritten path types. The processor determines, for each of the rewritten path types and remaining identified path types associated with the identified conversions, attribution credits for each event included in the path type. The processor creates, for each of the rewritten path types and remaining identified path types associated with the identified conversions, a rule for assigning the determined attribution credit to each event of the path type for which the rule is created.

Methods and systems for creating rules for assigning attribution credit across 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 is directed generally to systems and methods for the server side matching of web analytics and content viewing. According to the methods and systems disclosed herein, a first identifier is delivered to a client device when the client device accesses a first website. If the client device later accesses of a second website the first identifier can be processed by the system to determine if the client device previously accessed the first website.

Server side matching of offsite content viewing to onsite web analytics data

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

Methods, systems, and computer program products are provided for measuring effectiveness of content items included in a campaign. One example method includes providing a corpus of campaigns, where a campaign defines parameters for presentation that specify circumstances under which content items are presented to users in response to requests. The corpus is filtered by identifying one or more candidate campaigns, where each of the identified candidate campaigns is associated with a geographic region and includes one or more constraints that permit pausing distribution of content items without compromising campaign goals. For each candidate campaign, one or more experimental geographic locations included in the geographic region are determined that are substantially representative of the region. Presentation of at least one of the content items is paused for a time period, and content item effectiveness is measured by comparing resource conversions for experimental and control geographic locations.

Measuring content item effectiveness

Growing community of inventors

San Jose, CA, United States of America

Chao Cai