User lifetime revenue allocation associated with provisioned content recommendations
A personalized content recommendation provisioning method and system are described, according to various implementations. A token value allocation engine optimizes the allocation of content consumption revenue to publisher systems and recommendation source systems (e.g., the systems that provide the recommended content for presentation with the publisher system's native content) based on a model calculating and applying a life time or long term value (LTV) metric. The LTV metric for revenue is based on a detection of a how often a user system engages with content derived from or associated with a publisher system.
1. A method comprising:
establishing, by a processing device, a plurality of high-quality candidate content recommendation pools, wherein each of the plurality of high-quality candidate content recommendation pools comprises a plurality of candidate content recommendations;
generating a general grade associated with each of the plurality of candidate content recommendations in a first high-quality candidate content recommendation pool;
generating a user profile associated with a first user associated with a user system, wherein the user profile comprises registration information collected by an online registration of the first user;
generating a personalized grade associated with each of the plurality of candidate recommendations in the first high-quality candidate content recommendation pool, wherein the personalized grade is generated in view of registration information associated with the first user;
determining a recommendation scope associated with the first user in view of the personalized grade associated with each of the plurality of candidate content recommendations, wherein the content recommendation scope comprise one or more scoped content recommendations;
displaying, via a web page of a publisher system, the content recommendation scope to the user system;
detecting an initial user engagement metric corresponding to a first content recommendation of the content recommendation scope, wherein the first content recommendation is generated by a recommendation-source system; and
allocating a token value associated with the first content recommendation to the publisher system.
2. The method of claim 1 , wherein each of the plurality of high-quality candidate content recommendation pools is associated with a user trust measurement.
3. The method of claim 2 , further comprising determining the user interest measurement in view of a user trust signal.
4. The method of claim 1 , further comprising:
registering the first user by collecting registration information associated with the first user; and
generating a user profile associated with the first user, wherein the user profile comprises the registration information and user activity.
5. The method of claim 4 , wherein the user activity comprises information identifying content consumed by the first user collected by an associated tracking cookie.
6. The method of claim 1 , further comprising detecting a subsequent user engagement metric associated with the first user engagement metric.
7. The method of claim 6 , further comprising allocating a portion of the token value associated with the first content recommendation to the recommendation-source system.
8. The method of claim 1 , wherein the general grade associated with a first candidate content recommendation of the plurality of a candidate content recommendations is determined in view of an online click through rate (CTR) derived from aggregated user data associated with the first candidate content recommendation.
9. The method of claim 1 , wherein a set of candidate content recommendations of the content recommendation scope are filtered in view of a respective personalized grade associated with each of the candidate content recommendations of the content recommendation scope.
10. The method of claim 1 , further comprising establishing a first network comprising the publisher system, the recommendation-source system, and one or more additional recommendation-source systems.
11. A system comprising:
a memory comprising instructions; and
a processing device operatively coupled to the memory, the processing device to execute the instructions to:
establish a plurality of candidate content recommendation pools, wherein each of the plurality of candidate content recommendation pools comprises a plurality of candidate content recommendations;
generate a general grade associated with each of the plurality of candidate content recommendations in a first candidate content recommendation pool;
generate a user profile associated with a first user associated with a user system, wherein the user profile comprises registration information collected by an online registration of the first user;
generate a personalized grade associated with each of the plurality of candidate recommendations in the first candidate content recommendation pool, wherein the personalized grade is generated in view of registration information associated with the first user;
generate, for display via a publisher web page generated by a first publisher system, a first link to a first candidate content recommendation of the first candidate content recommendation pool;
detect, at the publisher web page, an initial user engagement metric corresponding to the first link by a user system; and
allocate, to the first publisher system, a full amount of a token value to the publisher system in response to detection of the initial user engagement.
12. The system of claim 11 , the processing device to execute the instructions to:
associate the token value with a network of a plurality of publisher systems comprising the first publisher system and the recommendation-source system, wherein the token value is an agreed upon amount of revenue associated with each user engagement metric.
13. The system of claim 12 , wherein the plurality of publisher systems register as members of the network and establish a monetary value to set as the token value.
14. The system of claim 11 , the processing device to execute the instructions to:
detect a set of one or more subsequent user engagement metrics corresponding to the first content recommendation; and
allocate a first portion of the token value associated with the first recommendation to the recommendation-source system in response to detection of each of the set of one or more subsequent user engagement metrics.
15. The system of claim 11 , the processing device to execute the instructions to:
determine a publisher system identifier corresponding to the first publisher system in response to detection of the first user engagement metric.
16. A non-transitory computer-readable storage medium comprising executable instructions that, when executed by a processing device, cause the processing device to:
establish a plurality of candidate content recommendation pools, wherein each of the plurality of candidate content recommendation pools comprises a plurality of candidate content recommendations;
generate a general grade associated with each of the plurality of candidate content recommendations in a first candidate content recommendation pool;
generate a user profile associated with a first user associated with a user system, wherein the user profile comprises registration information collected by an online registration of the first user;
generate a personalized grade associated with each of the plurality of candidate recommendations in the first candidate content recommendation pool, wherein the personalized grade is generated in view of registration information associated with the first user;
generate, for display via a publisher web page generated by a first publisher system, a first link to a first candidate content recommendation of the first candidate content recommendation pool;
detect, at the publisher web page, an initial user engagement metric corresponding to the first link by a user system; and
allocate, to the first publisher system, a full amount of a token value to the publisher system in response to detection of the initial user engagement.
17. The non-transitory computer-readable storage medium of claim 16 , the processing device to:
detect a set of one or more subsequent user engagement metrics corresponding to the first content recommendation; and
allocate a first portion of the token value associated with the first recommendation to the recommendation-source system in response to detection of each of the set of one or more subsequent user engagement metrics.
18. The non-transitory computer-readable storage medium of claim 16 , the processing device to:
determine a publisher system identifier corresponding to the first publisher system in response to detection of the first user engagement metric.
19. The non-transitory computer-readable storage medium of claim 16 , the processing device to execute the instructions to:
associate the token value with a network of a plurality of publisher systems comprising the first publisher system and the recommendation-source system, wherein the token value is an agreed upon amount of revenue associated with each user engagement metric.