Conversion crediting
AssigneeGoogle Inc.
InventorsSheng Ma, Sarah Masters, Fan Zhang
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer program products, for processing events related to presented content. In one aspect, a method includes determining a time window count of a number of advertising events associated with an advertisement during at least one time window before a conversion event; and determining a credit that represents a strength of an association between the advertisement and the conversion event, wherein determining a credit includes selecting a weighting model for the at least one time window count.
Claims20
A computer-implemented method, comprising:
- identifying, by a computer, one or more advertisement events associated with an advertisement, wherein each identified advertisement event is a user interaction with the advertisement that occurs prior to a conversion event, the conversion event being a predefined user interaction with a website;
- selecting, by the computer, two or more time windows, each time window encompassing a period of time prior to a conversion event;
- determining, by the computer and for each selected time window, a corresponding time window count by determining a number of the identified advertisement events occurring within the selected time window and before a conversion event;
- selecting, by the computer, a weighting factor for each selected time window;
- generating, by the computer and for each selected time window, a weighted time window count based on a function of each of the corresponding time window counts and the weighting factor for the selected time window, the weighted time window count indicating a value of the advertisement events that occurred within the time window relative to the advertisement events occurring in the other selected time windows;
- and
- determining, by the computer, an advertisement credit for the advertisement based at least in part on the weighted time window counts-for each selected time window, the advertisement credit indicating a strength of an association between the advertisement and the conversion event.
A system, comprising:
- a data processing apparatus;
- and
- a data store storing instructions that, when executed by the data processing apparatus, cause the data processing apparatus to perform operations comprising:
- identifying one or more advertisement events associated with an advertisement, wherein each identified advertisement event is a user interaction with the advertisement that occurs prior to a conversion event, the conversion event being a predefined user interaction with a website;
- selecting two or more time windows, each time window encompassing a period of time prior to a conversion event;
- determining, for each selected time window, a corresponding time window count by determining a number of the identified advertisement events occurring within the selected time window and before a conversion event;
- selecting a weighting factor for each selected time window;
- generating, for each selected time window, a weighted time window count based on a function of each of the corresponding time window counts and the weighting factor for the selected time window, the weighted time window count indicating a value of the advertisement events that occurred within the time window relative to the advertisement events occurring in the other selected time windows;
- and
- determining an advertisement credit for the advertisement based at least in part on the weighted time window counts for each selected time window, the advertisement credit indicating a strength of an association between the advertisement and the conversion event.
A non-transitory computer-readable medium comprising instructions that, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising:
- identifying one or more advertisement events associated with an advertisement, wherein each identified advertisement event is a user interaction with the advertisement that occurs prior to a conversion event, the conversion event being a predefined user interaction with a website;
- selecting two or more time windows, each time window encompassing a period of time prior to a conversion event;
- determining, for each selected time window, a corresponding time window count by determining a number of the identified advertisement events occurring within the selected time window and before a conversion event;
- selecting a weighting factor for each selected time window;
- generating, for each selected time window, a weighted time window count based on a function of each of the corresponding time window counts and the weighting factor for the selected time window, the weighted time window count indicating a value of the advertisement events that occurred within the time window relative to the advertisement events occurring in the other selected time windows;
- and
- determining an advertisement credit for the advertisement based at least in part on the weighted time window counts for each selected time window, the advertisement credit indicating a strength of an association between the advertisement and the conversion event.
A computer-implemented method, comprising:
- identifying, by one or more computers, one or more advertisement events associated with an advertisement, wherein each identified advertisement event is a user interaction with the advertisement that occurs prior to a conversion event;
- selecting, by the one or more computers, one or more time windows, each time window encompassing a period of time prior to a conversion event;
- determining, by the one or more computers and for each selected time window, a corresponding time window count by determining a number of the identified advertisement events occurring within the selected time window and before a conversion event;
- selecting, by the one or more computers, a weighting factor for each selected time window;
- generating, by the one or more computers and for each selected time window, a weighted time window count based on a function of each of the corresponding time window counts and the weighting factor for the selected time window;
- and
- determining, by the one or more computers, an advertisement credit for the advertisement based at least in part on the weighted time window counts for each selected time window, the advertisement credit indicating a strength of an association between the advertisement and the conversion event.
Dependencies are inferred from the claim text.