Machine learning model to estimate confidential data values based on job posting
In an example, one or more job postings, as well as corresponding confidential data values, are obtained from a social networking service. A first set of one or more features are extracted from the one or more job postings. The first set of one or more features and corresponding confidential data values are fed into a machine learning algorithm to train a confidential data value prediction model to output a predicted confidential data value for a candidate job posting. Then, the candidate job posting is obtained and a second set of one or more features are extracted from the candidate job posting. The extracted second set of one or more features is fed to the confidential data value prediction model, outputting the predicted confidential data value.
1. A system comprising:
A non-transitory machine-readable storage medium having instructions stored thereon, which, when executed by a processor, cause the system to:
obtain one or more job postings from an online network, the one or more job postings having been posted to the online network by one or more job posters;
obtain compensation values corresponding to the one or more job postings, the compensation values having been submitted to the online network by one or more users of the online network different than the one or more job posters;
extract a first set of one or more features from the one or more job postings;
feed the first set of one or more features and corresponding compensation values into a machine learning algorithm to train a compensation value prediction model to output a compensation value for a candidate job posting;
retrieve a first candidate job posting from a data store of the online network, the first candidate job posting having been posted to the online network;
extract a second set of one or more features from the retrieved first candidate job posting; and
feed the extracted second set of one or more features to the compensation value prediction model, outputting the predicted compensation value.
2. The system of claim 1 , wherein the first set of one or more features and the second set of one or more features are identical.
3. The system of claim 1 , wherein the compensation value prediction model is further trained to output a confidence score for each confidential data value prediction.
4. The system of claim 1 , further comprising calculating a statistical function on compensation values, including the predicted compensation value.
5. The system of claim 3 , wherein the instructions further cause the system to:
determine, for a statistical function, a threshold confidence score;
compare the confidence score to the threshold confidence score; and
in response to a determination that the confidence score transgresses the threshold confidence score, calculate the statistical function on confidential data values, including the predicted compensation value.
6. The system of claim 1 , wherein the machine learning algorithm is a logistical regression algorithm.
7. The system of claim 1 , wherein the machine learning algorithm is unsupervised.
8. A computerized method comprising:
obtaining one or more job postings from an online network, the one or more job postings having been posted to the online network by one or more job posters;
obtaining compensation values corresponding to the one or more job postings, the compensation values having been submitted to the online network by one or more users of the online network different than the one or more job posters;
extracting a first set of one or more features from the one or more job postings;
feeding the first set of one or more features and corresponding compensation values into a machine learning algorithm to train a compensation value prediction model to output a compensation value for a candidate job posting;
retrieving a first candidate job posting from a data store of the online network, the first candidate job posting having been posted to the online network;
extracting a second set of one or more features from the retrieved first candidate job posting; and
feeding the extracted second set of one or more features to the compensation value prediction model, outputting the predicted compensation value.
9. The method of claim 8 , wherein the first set of one or more features and the second set of one or more features are identical.
10. The method of claim 8 , wherein the compensation value prediction model is further trained to output a confidence score for each confidential data value prediction.
11. The method of claim 8 , calculating a statistical function on compensation values, including the predicted compensation value.
12. The method of claim 10 , further comprising:
determining, for a statistical function, a threshold confidence score;
comparing the confidence score to the threshold confidence score; and
in response to a determination that the confidence score transgresses the threshold confidence score, calculating the statistical function on confidential data values, including the predicted compensation value.
13. The method of claim 8 , wherein the machine learning algorithm is a logistical regression algorithm.
14. The method of claim 8 , wherein the machine learning algorithm is unsupervised.
15. A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform operations comprising:
obtaining one or more job postings from an online network, the one or more job postings having been posted to the online network by one or more job posters;
obtaining compensation values corresponding to the one or more job postings, the compensation values having been submitted to the online network by one or more users of the online network different than the one or more job posters;
extracting a first set of one or more features from the one or more job postings;
feeding the first set of one or more features and corresponding compensation values into a machine learning algorithm to train a compensation value prediction model to output a compensation value for a candidate job posting;
retrieving a first candidate job posting from a data store of the online network, the first candidate job posting having been posted to the online network;
extracting a second set of one or more features from the retrieved first candidate job posting; and
feeding the extracted second set of one or more features to the compensation value prediction model, outputting the predicted compensation value.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the first set of one or more features and the second set of one or more features are identical.
17. The non-transitory machine-readable storage medium of claim 15 , wherein the compensation value prediction model is further trained to output a confidence score for each confidential data value prediction.
18. The non-transitory machine-readable storage medium of claim 15 , calculating a statistical function on compensation values, including the predicted compensation value.
19. The non-transitory machine-readable storage medium of claim 17 , wherein the instructions further comprise:
determining, for a statistical function, a threshold confidence score;
comparing the confidence score to the threshold confidence score; and
in response to a determination that the confidence score transgresses the threshold confidence score, calculating the statistical function on confidential data values, including the predicted confidential data value.
20. The non-transitory machine-readable storage medium of claim 15 , wherein the machine learning algorithm is a logistical regression algorithm.