JOB APPLICANT QUALITY MODEL
A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein for Candidate Predictor Engine (“C.P. Engine”) instantiates data structure(s) modeled according to a plurality of job candidate predictor decision trees. The C.P. Engine encodes data representing a job candidate context feature set based on an attribute(s) of a target candidate account and an attribute(s) of a job posting. The C.P. Engine filters each respective feature from the job candidate context feature set through a job candidate predictor decision tree that corresponds to a same job candidate context feature type as the respective feature. The C.P. Engine generates prediction output based on each result of filtering through the job candidate predictor decision trees. The prediction output indicates a likelihood of the target candidate account being qualified for the job posting.
1 . A computer system, comprising:
a processor;
a memory device holding an instruction set executable on the processor to cause the computer system to perform operations comprising:
instantiating at least one data structure modeled according to a plurality of job candidate predictor decision trees, each job candidate predictor decision tree corresponding to a job candidate context feature type and comprising at least one learned decision tree branch label;
encoding data representing a job candidate context feature set based on at least one attribute of a target candidate account of a social network service and at least one attribute of a job posting on the social network service;
filtering at least one respective feature from the job candidate context feature set through a job candidate predictor decision tree that corresponds to a same job candidate context feature type as the respective feature; and
generating prediction output based on each result of filtering through the job candidate predictor decision trees, the prediction output indicating a likelihood of the target candidate account being qualified for the job posting.
2 . The computer system of claim 1 , wherein encoding data representing a job candidate context feature set based on at least one attribute of the target candidate account of a social network service and at least one attribute of a job posting on the social network service comprises:
encoding a job candidate feature data subset to include the at least one attribute of the target candidate account that corresponds with at least one pre-defined type of candidate feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting;
encoding a job feature data subset to include the at least one attribute of the job posting that corresponds with at least one pre-defined type of job feature that is learned as being predictive of whether the given job candidate is qualified for the given job posting; and
encoding a candidate-to-job comparison feature data subset to include a difference value between the at least one attribute of the target candidate account and the at least one attribute of the job posting that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether the given job candidate is qualified for the given job posting.
3 . The computer system of claim 2 , wherein the at least one pre-defined type of candidate feature comprises at least one of: a job function descriptor represented in a social network service profile of the target candidate account, a job industry descriptor represented in the social network service profile of the target candidate account, a job company size descriptor represented in the social network service profile of the target candidate account.
4 . The computer system of claim 2 , wherein the at least one pre-defined type of job feature comprises at least one of: a job function descriptor represented the job posting, a job industry descriptor represented in the job posting, a job company size descriptor represented in the job posting.
5 . The computer system of claim 2 , wherein encoding a candidate-to-job comparison feature data subset to include a difference value that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting comprises:
identifying years of candidate professional experience based on at least on employment time period descriptor in a social network service profile of the target candidate account;
identifying years of required professional experience described in the job posting;
calculating a years difference value to represent a difference between the years of candidate professional experience and the years of required professional experience; and
inserting the years difference value into the candidate-to-job comparison feature data subset as a respective comparison feature.
6 . The computer system of claim 5 , wherein inserting the years difference value into the candidate-to-job comparison feature data subset as a respective comparison feature comprises:
encoding the years difference value into a pre-defined data position for a years difference comparison feature in the candidate-to-job comparison feature data subset.
7 . The computer system of claim 2 , wherein encoding a candidate-to-job comparison feature data subset to include a difference value that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting comprises:
identifying each skill descriptor in a social network service profile of the target candidate account;
identifying each skill descriptor described in the job posting;
calculating a skill match value to represent a percentage of matching skill descriptors between the target candidate account's skill descriptors and each job posting's skill descriptors; and
inserting the skill match value into the candidate-to-job comparison feature data subset as a respective comparison feature.
8 . The computer system of claim 6 , wherein each skill descriptor in the social network service profile of the target candidate account comprises a respective skill descriptor selected by the target candidate account.
9 . The computer system of claim 6 , wherein each skill descriptor in the social network service profile of the target candidate account comprises a respective skill descriptor selected by a member account having a social network connection with the target candidate account.
10 . The computer system of claim 6 , wherein inserting the skill match value into the candidate-to-job comparison feature data subset as a respective comparison feature comprises:
encoding the skill match value into a pre-defined data position for a skill match comparison feature in the candidate-to-job comparison feature data subset.
11 . The computer system of claim 1 , wherein instantiating a plurality of job candidate decision trees, each job candidate decision tree comprising at least one learned decision tree branch label, comprises:
collecting, from within the social network service, logged interaction data comprising at least a first previous determination, by a first employer account, of a first candidate account as qualified for a first job posting and a second previous determination, by a second employer account, of a second candidate account as not qualified for a second job posting
12 . The computer system of claim 11 , wherein instantiating a plurality of job candidate decision trees, each job candidate decision tree comprising at least one learned decision tree branch label, further comprises:
executing a random forest process with the logged interaction data to build each job candidate decision tree.
13 . The computer system of claim 12 , wherein executing a random forest process with the logged interaction data to build each job candidate decision tree comprises:
learning a branch label for each branch of each job candidate decision tree
based on at least one attribute of the logged interaction data.
14 . A computer-implemented method, comprising:
instantiating at least one data structure modeled according to a plurality of job candidate predictor decision trees, each job candidate predictor decision tree corresponding to a job candidate context feature type and comprising at least one learned decision tree branch label;
encoding data, via at least one processor, representing a job candidate context feature set based on at least one attribute of a target candidate account of a social network service and at least one attribute of a job posting on the social network service;
filtering at least one respective feature from the job candidate context feature set through a job candidate predictor decision tree that corresponds to a same job candidate context feature type as the respective feature; and
generating prediction output based on each result of filtering through the job candidate predictor decision trees, the prediction output indicating a likelihood of the target candidate account being qualified for the job posting.
15 . The computer-implemented method of claim 14 , wherein encoding data representing a job candidate context feature set based on at least one attribute of target candidate account of a social network service and at least one attribute of a job posting on the social network service comprises:
encoding a job candidate feature data subset to include the at least one attribute of the target candidate account that corresponds with at least one pre-defined type of candidate feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting;
encoding a job feature data subset to include the at least one attribute of the job posting that corresponds with at least one pre-defined type of job feature that is learned as being predictive of whether the given job candidate is qualified for the given job posting; and
encoding a candidate-to-job comparison feature data subset to include a difference value between the at least one attribute of the target candidate account and the at least one attribute of the job posting that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether the given job candidate is qualified for the given job posting.
16 . The computer-implemented method of claim 15 , wherein encoding a candidate-to-job comparison feature data subset to include a difference value that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting comprises:
identifying years of candidate professional experience based on at least on employment time period descriptor in a social network service profile of the target candidate account;
identifying years of required professional experience described in the job posting;
calculating a years difference value to represent a difference between the years of candidate professional experience and the years of required professional experience; and
inserting the years difference value into the candidate-to-job comparison feature data subset as a respective comparison feature.
17 . The computer-implemented method of claim 16 , wherein inserting the years difference value into the candidate-to-job comparison feature data subset as a respective comparison feature comprises:
encoding the years difference value into a pre-defined data position for a years difference comparison feature in the candidate-to-job comparison feature data subset.
18 . The computer-implemented method of claim 15 , wherein encoding a candidate-to-job comparison feature data subset to include a difference value that corresponds with a pre-defined type of comparison feature that is learned as being predictive of whether a given job candidate is qualified for a given job posting comprises:
identifying each skill descriptor in a social network service profile of the target candidate account;
identifying each skill descriptor described in the job posting;
calculating a skill match value to represent a percentage of matching skill descriptors between the target candidate account's skill descriptors and each job posting's skill descriptors; and
inserting the skill match value into the candidate-to-job comparison feature data subset as a respective comparison feature.
19 . The computer system of claim 18 , wherein each skill descriptor in the social network service profile of the target candidate account comprises a respective skill descriptor selected by the target candidate account.
20 . A non-transitory computer-readable medium storing executable instructions thereon, which, when executed by a processor, cause the processor to perform operations including:
instantiating at least one data structure modeled according to a plurality of job candidate predictor decision trees, each job candidate predictor decision tree corresponding to a job candidate context feature type and comprising at least one learned decision tree branch label;
encoding data representing a job candidate context feature set based on at least one attribute of a target candidate account of a social network service and at least one attribute of a job posting on the social network service;
filtering at least one respective feature from the job candidate context feature set through a job candidate predictor decision tree that corresponds to a same job candidate context feature type as the respective feature; and
generating prediction output based on each result of filtering through the job candidate predictor decision trees, the prediction output indicating a likelihood of the target candidate account being qualified for the job posting.