Identifying similar items based on global interaction history
One embodiment sets forth technique for computing a similarity score between two digital items is computed based on interaction histories associated with global users and interaction histories associated with local users. Global counts indicating the number of interactions associated with each unique pair of digital items are weighted based on a mixing rate. The weighted global counts are then combined with local counts to compute total counts. An effective interaction probability indicating the likelihood of a user interacting with one digital item in the pair of digital items after interacting with the other digital item in the pair is computed based on the total counts. The effective interaction probability is then corrected for noise, resulting in a similarity score indicating the similarity between the pair of digital items.
1. A computer-implemented method, the method comprising:
in response to a user interacting with a first digital content item included in a local catalogue via a content browser, generating, at a web server computing system, a web application interface that includes a plurality of interface elements, wherein each interface element included in the plurality of interface elements is individually selectable when the web application interface is displayed;
identifying, at the web server computing system, a different digital content item for each interface element included in the plurality of interface elements, wherein a second digital content item identified for a first interface element included in the plurality of interface elements is identified by:
determining a local count associated with the first digital content item based on first interaction data associated with a local group of users including the user, wherein the local count indicates a number of times the local group of users has interacted with a second digital content item in the local catalogue after interacting with the first digital content item,
determining a global count associated with the first digital content item based on second interaction data associated with a global group of users, wherein the global count indicates a number of times the global group of users has interacted with the second digital content item after interacting with the first digital content item,
combining the local count and the global count based on a popularity associated with the second digital content item to compute an interaction probability that indicates a likelihood of a particular user within the local group of users interacting with the second digital content item after interacting with the first digital content item,
modifying the interaction probability based on a noise associated with the popularity of the second digital content item, a noise in the first interaction data, or a noise in the second interaction data; and
identifying, based on the modified interaction probability, the second digital content item for presentation within a first interface element in the plurality of interface elements; and
transmitting, from the web server computing system to the content browser, the web application interface in order to present the first digital content item within the first interface element, wherein the first interface element is selectable when the web application interface is displayed within the content browser.
2. The method of claim 1 , further comprising filtering the interaction data associated with the global group of users to remove data related to items that are not included in the local catalogue.
3. The method of claim 1 , wherein combining the global count and the local count comprises determining a mixing rate that indicates a weight applied to the interaction data associated with a global group of users.
4. The method of claim 3 , wherein combining the global count and the local count comprises computing a global probability that indicates a likelihood that a global user within the global group of users would interact with the second item after interacting with the first item.
5. The method of claim 4 , wherein combining the global count and the local count further comprises computing a local probability that indicates a likelihood that a local user within the local group of users would interact with a given item after interacting with a previously-presented item.
6. The method of claim 5 , wherein combining the global count and the local count further comprises weighting the global probability according to the mixing rate, and then combining the local probability and the weighted global probability to compute the interaction probability.
7. The method of claim 1 , wherein the popularity associated with the second digital item indicates a likelihood that the particular user would randomly interact with the given item.
8. The method of claim 1 , wherein identifying the second digital content item comprises computing a similarity score that indicates the similarity between the first digital content item and the second digital content item based on the interaction probability and the popularity associated with the second digital content item, wherein the second digital content item is identified for presentation within the first interface element based on the similarity score.
9. The method of claim 8 , wherein computing the similarity score comprises computing a ratio of the interaction probability and a popularity score.
10. The method of claim 8 , further comprising applying a noise correction function to the similarity score to filter the data that was captured in a set of global counts or a set of local counts.
11. One or more non-transitory computer readable media storing instructions that, when executed by one or more processors, cause the one or more processors to performs the steps of:
in response to a user interacting with a first digital content item included in a local catalogue via a content browser, generating, at a web server computing system, a web application interface that includes a plurality of interface elements, wherein each interface element included in the plurality of interface elements is individually selectable when the web application interface is displayed;
identifying, at the web server computing system, a different digital content item for each interface element included in the plurality of interface elements, wherein a second digital content item identified for a first interface element included in the plurality of interface elements is identified by:
determining a local count associated with the first digital content item based on first interaction data associated with a local group of users including the user, wherein the local count indicates a number of times the local group of users has interacted with a second digital content item in the local catalogue after interacting with the first digital content item,
determining a global count associated with the first digital content item based on second interaction data associated with a global group of users, wherein the global count indicates a number of times the global group of users has interacted with the second digital content item after interacting with the first digital content item,
combining the local count and the global count based on a popularity associated with the second digital content item to compute an interaction probability that indicates a likelihood of a particular user within the local group of users interacting with the second digital content item after interacting with the first digital content item,
modifying the interaction probability based on a noise associated with the popularity of the second digital content item, a noise in the first interaction data, or a noise in the second interaction data; and
identifying, based on the modified interaction probability, the second digital content item for presentation within a first interface element in the plurality of interface elements; and
transmitting, from the web server computing system to the content browser, the web application interface in order to present the first digital content item within the first interface element, wherein the first interface element is selectable when the web application interface is displayed within the content browser.
12. The one or more non-transitory computer readable media of claim 11 , further comprising filtering the interaction data associated with the global group of users to remove data related to items that are not included in the local catalogue.
13. The one or more non-transitory computer readable media of claim 11 , wherein combining the global count and the local count comprises determining a mixing rate that indicates a weight applied to the interaction data associated with a global group of users.
14. The one or more non-transitory computer readable media of claim 13 , wherein combining the global count and the local count comprises computing a global probability that indicates a likelihood that a global user within the global group of users would interact with the second item after interacting with the first item.
15. The one or more non-transitory computer readable media of claim 14 , wherein combining the global count and the local count further comprises computing a local probability that indicates a likelihood that a local user within the local group of users would interact with a given item after interacting with a previously-presented item.
16. The one or more non-transitory computer readable media of claim 15 , wherein combining the global count and the local count further comprises weighting the global probability according to the mixing rate, and then combining the local probability and the weighted global probability to compute the interaction probability.
17. The one or more non-transitory computer readable media of claim 11 , wherein the popularity associated with the second digital item indicates a likelihood that the particular user would randomly interact with the given item.
18. The one or more non-transitory computer readable media of claim 11 , wherein identifying the second digital content item comprises computing a similarity score that indicates the similarity between the first digital content item and the second digital content item based on the interaction probability and the popularity associated with the second digital content item, wherein the second digital content item is identified for presentation within the first interface element based on the similarity score.
19. The one or more non-transitory computer readable media of claim 18 , wherein computing the similarity score comprises computing a ratio of the interaction probability and a popularity score.
20. A computer system, comprising:
a memory storing one or more instructions; and
a server computing system configured to execute the one or more instructions to:
in response to a user interacting with a first digital content item included in a local catalogue via a content browser, generating, at a web server computing system, a web application interface that includes a plurality of interface elements, wherein each interface element included in the plurality of interface elements is individually selectable when the web application interface is displayed;
identifying, at the web server computing system, a different digital content item for each interface element included in the plurality of interface elements, wherein a second digital content item identified for a first interface element included in the plurality of interface elements is identified by:
determining a local count associated with the first digital content item based on first interaction data associated with a local group of users including the user, wherein the local count indicates a number of times the local group of users has interacted with a second digital content item in the local catalogue after interacting with the first digital content item,
determining a global count associated with the first digital content item based on second interaction data associated with a global group of users, wherein the global count indicates a number of times the global group of users has interacted with the second digital content item after interacting with the first digital content item,
combining the local count and the global count based on a popularity associated with the second digital content item to compute an interaction probability that indicates a likelihood of a particular user within the local group of users interacting with the second digital content item after interacting with the first digital content item,
modifying the interaction probability based on a noise associated with the popularity of the second digital content item, a noise in the first interaction data, or a noise in the second interaction data, and
identifying, based on the modified interaction probability, the second digital content item for presentation within a first interface element in the plurality of interface elements; and
transmitting, from the web server computing system to the content browser, the web application interface in order to present the first digital content item within the first interface element, wherein the first interface element is selectable when the web application interface is displayed within the content browser.