Inferring service providers
View Patent ↗A system and method for inferring service providers are provided. In example embodiments, member data of members of a social networking service is accessed. From the member data, it is inferred that a particular member among the members of the social networking service is a freelancer member. A service request that the freelancer member is capable of fulfilling is identified based on a service request skill associated with the service request and a freelancer skill of the freelancer member. An option for the freelancer member to fulfill the service request is presented on a user interface of a user device of the freelancer member.
1. A method comprising:
accessing member data of members of an online service;
obtaining labels for the member data, the labels each indicating whether a corresponding member data is associated with a member who is a freelancer member or who is not a freelancer member;
training a machine-learned prediction model using the member data and the labels as ground truth data;
detecting a member event, associated with a first member;
in response to the detecting:
identifying a service request based on the member event, wherein the identifying comprises:
accessing historical service data indicating services other members of the online service have used along with member events of the other members; and
correlating the member events of the other members with services used by the other members to identify a rule to predict what services may be needed or desired following the member event;
accessing member data for a first plurality of members of the online service;
extracting features from the member data for the first plurality of members of the online service;
using the machine-learned prediction model to infer that one or more of the members in the first plurality of members are freelancer members based on their similarity to members in the training data that have been labeled as freelancer members, the similarity based on the extracted features;
and
identifying that the service request is capable of being fulfilled by one or more of the inferred one or more freelancer members based on a service request skill associated with the service request and a freelancer skill of the corresponding freelancer member;
causing presentation, on a user interface of a user device of at least one of the one or more members in the first plurality of members inferred to be freelancer members and capable of fulfilling the service request.
2. The method of claim 1 , wherein the features include job titles.
3. The method of claim 1 , wherein the machine-learned prediction model is a logistic regression model.
4. The method of claim 1 , wherein the machine-learned prediction model is a Naïve Bayes model.
5. The method of claim 1 , wherein the machine-learned prediction model is a support vector machines model.
6. The method of claim 1 , wherein the machine-learned prediction model is a decision trees model.
7. The method of claim 1 , wherein the machine-learned prediction model is a neural network model.
8. The method of claim 1 , wherein the machine-learned prediction model is further used to infer that one or more of the one or more members in the first plurality of members has a particular skill corresponding to the service request.
9. The method of claim 8 , wherein the machine-learned prediction model is further used to calculate a match score for each of the one or more of the one or more members in the first plurality of members, the match score indicative of a level of capability of fulfilling the service request.
10. A system comprising:
a non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to:
access member data of members of an online service;
obtain labels for the member data, the labels each indicating whether a corresponding member data is associated with a member who is a freelancer member or who is not a freelancer member;
train a machine-learned prediction model using the member data and the labels as ground truth data;
detect a member event associated with a first member;
in response to the detecting:
identify a service request based on the member event, wherein the identifying comprises:
access historical service data indicating services other members of the online service have used along with member events of the other members; and
correlate the member events of the other members with services used by the other members to identify a rule to predict what services may be needed or desired following the member event;
access member data for a first plurality of members of the online service;
extract features from the member data for the first plurality of members of the online service;
use the machine-learned prediction model to infer that one or more of the members in the first plurality of members are freelancer members based on their similarity to members in the training data that have been labeled as freelancer members, the similarity based on the extracted features; and
identify that the service request is capable of being fulfilled by one or more of the inferred one or more freelancer members based on a service request skill associated with the service request and a freelancer skill of the corresponding freelancer member;
cause presentation, on a user interface of a user device of at least one of the one or more members in the first plurality of members inferred to be freelancer members and capable of fulfilling the service request.
11. The system of claim 10 , wherein the features include job titles.
12. A machine-readable medium having no transitory signals and storing instructions that, when executed by at least one processor of a machine, cause the machine to perform operations comprising:
accessing member data of members of an online service;
obtaining labels for the member data, the labels each indicating whether a corresponding member data is associated with a member who is a freelancer member or who is not a freelancer member;
training a machine-learned prediction model using the member data and the labels as ground truth data;
detecting a member event associated with a first member;
in response to the detecting:
identifying a service request based on the member event, wherein the identifying comprises:
accessing historical service data indicating services other members of the online service have used along with member events of the other members; and
correlating the member events of the other members with services used by the other members to identify a rule to predict what services may be needed or desired following the member event;
accessing member data for a first plurality of members of the online service;
extracting features from the member data for the first plurality of members of the online service;
using the machine-learned prediction model to infer that one or more of the members in the first plurality of members are freelancer members based on their similarity to members in the training data that have been labeled as freelancer members, the similarity based on the extracted features; and
identifying that the service request is capable of being fulfilled by one or more of the inferred one or more freelancer members based on a service request skill associated with the service request and a freelancer skill of the corresponding freelancer member;
causing presentation, on a user interface of a user device of at least one of the one or more members in the first plurality of members inferred to be freelancer members and capable of fulfilling the service request.
13. The machine-readable medium of claim 12 , wherein the features include job titles.
14. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is a logistic regression model.
15. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is a Naïve Bayes model.
16. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is a support vector machines model.
17. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is a decision trees model.
18. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is a neural network model.
19. The machine-readable medium of claim 12 , wherein the machine-learned prediction model is further used to infer that one or more of the one or more members in the first plurality of members has a particular skill corresponding to the service request.
20. The machine-readable medium of claim 19 , wherein the machine-learned prediction model is further used to calculate a match score for each of the one or more of the one or more members in the first plurality of members, the match score indicative of a level of capability of fulfilling the service request.