Advertising cannibalization management
A system and method for advertising cannibalization management are provided. In example embodiments, historical data comprising advertisement revenue, advertisement parameters, and a cannibalization metric are accessed. The cannibalization metric is indicative of sales loss associated with an advertisement presentation. A value for at least one of the advertisement parameters that, when used, causes a desired advertisement revenue with respect to a bounded cannibalization metric is determined by analyzing the historical data. An advertisement is presented, in real time, on a user interface of a client device using the determined value.
1. A system comprising:
one or more processors; and
one or more machine-readable media communicatively coupled to the one or more processors and having instructions stored thereon that, in response to execution by the one or more processors, cause the system to perform operations, the operations comprising:
monitoring one or more user navigation metrics, including:
user selection of displayed links when navigating a website that includes multiple internal pages, wherein one or more of the internal pages include a plurality of links; and
multiple link parameters of selected links;
storing historical data that includes the user navigation metrics based on the monitoring;
obtaining, based on the historical data a cannibalization metric that corresponds to the plurality of links presented on an internal page, the cannibalization metric associated with navigation away from the website;
determining a relationship between the cannibalization metric and a particular cannibalization covariate that corresponds to the plurality of links, the particular cannibalization covariate predicting navigation away from the website;
determining a relationship between a first link parameter and the particular cannibalization covariate;
determining, based on the relationship between the first link parameter and the particular cannibalization covariate, a set of values of the first link parameter that correspond to less than a threshold amount of navigation away from the website;
selecting a value of the first link parameter that is within the set of values; and
controlling an amount of user navigation away from the website by causing presentation of a link using the selected value of the first link parameter that is within the set of values.
2. The system of claim 1 , wherein the user navigation metrics further include:
number of times a link to the same location was viewed.
3. The system of claim 1 , wherein the historical data further includes:
one or more historical values of the cannibalization metric; and
estimated value of displaying one or more links.
4. The system of claim 3 , wherein the historical data further includes:
one or more non-selection navigation activities.
5. The system of claim 1 , wherein the multiple link parameters include:
link size and link position.
6. A method, comprising:
monitoring, by a computing system, one or more user navigation metrics, including:
user selection of displayed links when navigating a website that includes multiple internal pages, wherein one or more of the internal pages include a plurality of links; and
multiple link parameters of selected links;
storing, by the computing system, historical data that includes the user navigation metrics based on the monitoring;
obtaining, by the computing system based on the historical data, including the user selection of displayed links, a cannibalization metric that corresponds to the plurality of links presented on an internal page, the cannibalization metric associated with navigation away from the website;
determining, by the computing system, a relationship between the cannibalization metric and a particular cannibalization covariate that corresponds to the plurality of links, the particular cannibalization covariate predicting navigation away from the website;
determining, by the computing system, a relationship between a first link parameter and the particular cannibalization covariate;
determining, by the computing system based on the relationship between the first link parameter and the particular cannibalization covariate, a set of values of the first link parameter that correspond to less than a threshold amount of navigation away from the website;
selecting, by the computing system, a value of the first link parameter that is within the set of values; and
controlling, by the computing system, an amount of user navigation away from the website by causing presentation of a link using the selected value of the first link parameter that is within the set of values.
7. The method of claim 6 , wherein the historical data further includes:
number of times a link to the same location was viewed.
8. The method of claim 6 , wherein the historical data further includes:
one or more historical values of the cannibalization metric; and
estimated value of displaying one or more links.
9. The method of claim 8 , wherein the historical data further includes:
one or more non-selection navigation activities.
10. The method of claim 6 , wherein the multiple link parameters include:
link size and link position.
11. The method of claim 10 , wherein the multiple link parameters further include:
number of times a link to the same location is displayed on a page; and
entity maintaining external page targeted by a link.
12. The method of claim 6 , wherein the determining the set of values of the first link parameter is based on an estimated value of displaying one or more links.
13. The method of claim 6 , wherein the determining the set of values of the first link parameter is based on a prediction that the set of values of the first link parameter maintains the cannibalization metric within a bounded range.
14. A non-transitory computer-readable medium having instructions stored thereon that are executable by a computing device to perform operations comprising:
monitoring one or more user navigation metrics, including:
user selection of displayed links when navigating a website that includes multiple internal pages, wherein one or more of the internal pages include a plurality of links; and
multiple link parameters of selected links;
storing historical data that includes the user navigation metrics based on the monitoring;
obtaining, based on the historical data, including the user selection of displayed links, a cannibalization metric that corresponds to the plurality of links presented on an internal page, the cannibalization metric associated with navigation away from the website;
determining a relationship between the cannibalization metric and a particular cannibalization covariate that corresponds to the plurality of links, the particular cannibalization covariate predicting navigation away from the website;
determining a relationship between a first link parameter and the particular cannibalization covariate;
determining, based on the relationship between the first link parameter and the particular cannibalization covariate, a set of values of the first link parameter that correspond to less than a threshold amount of navigation away from the website;
selecting a value of the first link parameter that is within the set of values; and
controlling an amount of user navigation away from the website by causing presentation of a link using the selected value of the first link parameter that is within the set of values.
15. The non-transitory computer-readable medium of claim 14 , wherein the historical data further includes:
number of times a link to the same location was viewed.
16. The non-transitory computer-readable medium of claim 14 , wherein the historical data further includes:
one or more historical values of the cannibalization metric.
17. The non-transitory computer-readable medium of claim 16 , wherein the historical data further includes:
estimated value of displaying one or more links; and
one or more non-selection navigation activities.
18. The non-transitory computer-readable medium of claim 14 , wherein the multiple link parameters include:
link size and link position; and
number of times a link to the same location is displayed on a page.
19. The non-transitory computer-readable medium of claim 18 , wherein the multiple link parameters include:
entity maintaining external page targeted by the link.