Performing query-time attribution channel modeling

Patent metadata

Field	Value
Publication number	US-10970338-B2
Application number	US-201816189739-A
Country	US
Kind code	B2
Filing date	Nov 13, 2018
Priority date	Nov 13, 2018
Publication date	Apr 6, 2021
Grant date	Apr 6, 2021

Abstract

The present disclosure relates to performing attribution channel modeling in real time using touchpoint data that corresponds to a user-specified set of channels and is retrieved from a database using a user-specified attribution model. For example, in one or more embodiments, a system stores raw data in an attribution database that comprises an aggregator and a plurality of nodes. In particular, each node stores touchpoint data associated with a different user. Upon receiving a query, the system can, in real time, retrieve subsets of the touchpoint data that corresponds to a user-defined set of distribution channels in accordance with a user-specified attribution model. The system then combines the subsets of touchpoint data using the aggregator and generates the digital attribution report using the combined data.

First claim

What is claimed is:

1. In a digital medium environment for collecting and analyzing analytics data about network communications, a method for generating digital attribution reports in real-time comprising:
performing a step for storing touchpoint data in an attribution database in a manner that supports query-time attribution channel modeling;
receiving a query to generate a digital attribution report, the query indicating a user-specified set of distribution channels and a user-specified attribution model; and
performing, in real time in response to the query, a step for generating the digital attribution report for the user-specified set of distribution channels using the user-specified attribution model based on the touchpoint data stored in the attribution database.

2. The method of claim 1 , wherein receiving the query to generate the digital attribution report comprises receiving a request to generate the digital attribution report for a plurality of sub-channel elements.

3. The method of claim 1 , wherein the touchpoint data comprises one or more touchpoints and a timestamp associated with each of the one or more touchpoints.

4. The method of claim 1 , wherein the user-specified set of distribution channels comprises at least one of:
a paid search channel;
an organic search channel;
a referring domain channel;
a display channel;
a social network channel;
an email channel; or
a direct access channel.

5. A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computing device to:
store touchpoint data in an attribution database comprising an aggregator and a plurality of nodes, wherein each node corresponds to a given user and comprises a processing unit that receives and stores touchpoint data associated with the given user;
receive a query to generate a digital attribution report, the query indicating a user-specified set of distribution channels and a user-specified attribution model; and
after receiving the query and in real time:
retrieve, from nodes of the plurality of nodes, subsets of touchpoint data by utilizing the processing unit of a given node of the nodes to retrieve a subset of touchpoint data associated with a user corresponding to the given node based on the user-specified set of distribution channels and the user-specified attribution model;
combine, using the aggregator, the subsets of touchpoint data corresponding to the user-specified set of distribution channels in accordance with the user-specified attribution model;
generate the digital attribution report using the combined subsets of touchpoint data; and
provide the digital attribution report for display.

6. The non-transitory computer readable storage medium of claim 5 , wherein:
an instance of touchpoint data comprises an indication of a touchpoint and a timestamp associated with the touchpoint, and
the instructions, when executed by the at least one processor, cause the computing device to store the touchpoint data in the attribution database by storing, in each node, instances of touchpoint data chronologically based on the timestamp associated with each touchpoint of a corresponding user.

7. The non-transitory computer readable storage medium of claim 5 , wherein the instructions, when executed by the at least one processor, cause the computing device to, retrieve, from the nodes of the plurality of nodes, the subsets of touchpoint data by utilizing the processing unit of the given node of the nodes to retrieve the subset of touchpoint data associated with the user corresponding to the given node based on the user-specified set of distribution channels and the user-specified attribution model by utilizing the processing unit of the given node to filter a subset of touchpoints that correspond to the user-specified set of distribution channels in accordance with the user-specified attribution model.

8. The non-transitory computer readable storage medium of claim 5 , wherein the attribution database further comprises a plurality of intermediate aggregators, wherein each intermediate aggregator is associated with, and aggregates data from, a different subset of the nodes of the plurality of nodes.

9. The non-transitory computer readable storage medium of claim 8 ,
further comprising instructions that, when executed by the at least one processor, cause the computing device to aggregate, using each intermediate aggregator, the subsets of touchpoint data from the subset of the nodes corresponding to each intermediate aggregator to generate sets of aggregated touchpoint data,
wherein the instructions, when executed by the at least one processor, cause the computing device to combine, using the aggregator, the subsets of touchpoint data by combining the sets of aggregated touchpoint data from the plurality of intermediate aggregators.

10. The non-transitory computer readable storage medium of claim 5 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
receive a second query to generate a second digital attribution report second query indicating the user-specified set of distribution channels and a second user-specified attribution model;
after receiving the second query and in real time:
retrieve from the nodes of the plurality of nodes, second subsets of touchpoint data by utilizing the processing unit of the given node of the nodes to retrieve a second subset of touchpoint data associated with the user corresponding to the given node based on the user-specified set of distribution channels and the second user-specified attribution model;
combine, using the aggregator, the second subsets of touchpoint data corresponding to the user-specified set of distribution channels in accordance with the second user-specified attribution model; and
generate the second digital attribution report using the combined second subsets of touchpoint data; and

provide the second digital attribution report for display simultaneously with the digital attribution report.

11. The non-transitory computer readable storage medium of claim 5 , wherein the user-specified attribution model comprises a custom attribution model comprising a user-specified set of weights to be applied to the subsets of touchpoint data corresponding to the user-specified set of distribution channels.

12. The non-transitory computer readable storage medium of claim 5 , wherein the user-specified attribution model comprises a time decay attribution model comprising a user-specified half-life to be applied to the subsets of touchpoint data corresponding to the user-specified set of distribution channels.

13. A system comprising:
a memory component comprising:
an aggregator; and
a plurality of nodes, wherein each node corresponds to a given user and comprises a processing unit that is configured to receive and sequentially store touchpoint data associated with the given user;

at least one server; and
at least one non-transitory computer readable storage medium comprising instructions that, when executed by the at least one server, cause the system to:
receive a query to generate a digital attribution report the query indicating a user-specified set of distribution channels and a user-specified attribution model; and
after receiving the query and in real time:
send, to the plurality of nodes, a request for touchpoint data corresponding to the user-specified set of distribution channels based on the user-specified attribution model;
retrieve, from nodes of the plurality of nodes, subsets of touchpoint data to send to the aggregator by utilizing the processing

Assignees

• Adobe Inc

Inventors

• Paulsen Trevor
• Andrus Ivan
• Turchenko Vladislav
• Dehart Dirk
• Wilcox David
• Jarvis Brian

Classifications

• G06Q10/067 Primary

  Enterprise or organisation modelling · CPC title

• G06F16/2477

  Temporal data queries · CPC title

• G06F16/244

  Grouping and aggregation · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06F16/9038 Primary

  Presentation of query results · CPC title