Multi-touch attribution model for valuing impressions and other online activities
AssigneeAggregate Knowledge, Inc.
InventorsMatthew David Curcio, Robert Lawrence Grzywinski, Benjamin Charles Linsay
Life of this patent
Estimating the term…
Abstract
To implement a multi-touch attribution model, a conversion event resulting from user activity is programmatically detected. A set of events that precede the conversion event is identified. Respective events of the set occur on respective websites. The conversion event is attributed to multiple websites of the respective websites.
Claims18
A method of operating a computing system, the method comprising:
- detecting, with one or more computing devices, a conversion event indicating an online behavior of a user;
- determining, with one or more computing devices, an interaction of the user with a website, an advertisement on the web site, or a combination thereof indicating an event, including a purchase of an item, a view of the web site, a hover over the advertisement on the website, an input, or a combination thereof that precedes the conversion event;
- assigning, with one or more computing devices, a value to the interaction;
- computing, with one or more computing devices, a composite weighting function based on multiplying the value of the interaction and an attribution decay function;
- computing, with one or more computing devices, a normalized composite weighting based on normalizing the composite weighting function;
- and
- transmitting, with one or more computing devices, the normalized composite weighting function for reporting to an end user device.
A non-transitory computer readable medium with instructions stored thereon that, when executed by a computing system, cause the computing system to perform operations comprising:
- detecting a conversion event indicating an online behavior of a user;
- determining an interaction of the user with a website, an advertisement on the website, or a combination thereof indicating an event, including a purchase of an item, a view of the web site, a hover over the advertisement on the web site, an input, or a combination thereof that precedes the conversion event;
- assigning a value to the interaction;
- computing a composite weighting function based on multiplying the value of the interaction and an attribution decay function;
- computing a normalized composite weighting based on normalizing the composite weighting function;
- and
- transmitting the normalized composite weighting function for reporting to an end user device.
A computing system comprising:
- a processor configured to:
- detect a conversion event indicating an online behavior of a user,
- determine an interaction of the user with a website, an advertisement on the website, or a combination thereof indicating an event, including a purchase of an item, a view of the website, a hover over the advertisement on the website, an input, or a combination thereof that precedes the conversion event,
- assign a value to the interaction,
- compute a composite weighting function based on multiplying the value of the interaction and an attribution decay function, and
- compute a normalized composite weighting based on normalizing the composite weighting function;
- and
- a communication interface, coupled to the processor, configured to:
- transmit the normalized composite weighting function for reporting to an end user device.
Dependencies are inferred from the claim text.