Machine learning algorithm for user engagement based on confidential data statistical information

1. A computerized method comprising:

obtaining sample member usage information for a plurality of members in a social networking service, the sample member usage information comprising a plurality of member profiles and, for each member profile, associated usage information regarding graphical user interface interactions with the social networking service, the sample member usage information further comprising, for each member profile, a label indicating an estimated engagement score for the corresponding member, the estimated engagement score indicating a likelihood that the corresponding member will increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members;

for each of the plurality of members:

extracting a first plurality of features from the sample member usage information for the member;

feeding the first plurality of features and the label corresponding to the member into a supervised machine learning algorithm to train an engagement score model to calculate an engagement score for a particular member indicating a probability that the particular member would increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members, the particular member being unable to view the confidential data submitted by other members;

obtaining member usage information corresponding to a first member of a social networking service;

extracting a second plurality of features from the member usage information corresponding to the first member;

inputting the second plurality of features into the engagement model to obtain an engagement score for the first member; and

determining whether or not to provide statistical information to the first member about confidential data submitted by other members based on the engagement score for the first member.

2. The computerized method of claim 1 , wherein the first plurality of features are identical to the second plurality of features.

3. The computerized method of claim 1 , wherein the first plurality of features are further extracted from a member profile for the member.

4. The computerized method of claim 1 , wherein the first plurality of features include measurements of communications sent via the social networking service.

5. The computerized method of claim 1 , wherein the first plurality of features include transaction attributes.

6. The computerized method of claim 1 , wherein the supervised machine learning algorithm is a binary logistic regression model.

7. The computerized method of claim 1 , wherein the determining includes comparing the engagement score for the first member to a threshold value corresponding to attributes of the first member.

8. A system comprising:

a computer-readable medium having instructions stored there on, which, when executed by a processor, cause the system to:

obtain sample member usage information for a plurality of members in a social networking service, the sample member usage information comprising a plurality of member profiles and, for each member profile, associated usage information regarding graphical user interface interactions with the social networking service, the sample member usage information further comprising, for each member profile, a label indicating an estimated engagement score for the corresponding member, the estimated engagement score indicating a likelihood that the corresponding member will increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members;

for each of the plurality of members:

extract a first plurality of features from the sample member usage information for the member;

feed the first plurality of features and the label corresponding to the member into a supervised machine learning algorithm to train an engagement score model to calculate an engagement score for a particular member indicating a probability that the particular member would increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members, the particular member being unable to view the confidential data submitted by other members;

obtain member usage information corresponding to a first member of a social networking service;

extract a second plurality of features from the member usage information corresponding to the first member;

input the second plurality of features into the engagement model to obtain an engagement score for the first member; and

determine whether or not to provide statistical information to the first member about confidential data submitted by other members based on the engagement score for the first member.

9. The system of claim 8 , wherein the first plurality of features are identical to the second plurality of features.

10. The system of claim 8 , wherein the first plurality of features are further extracted from a member profile for the member.

11. The system of claim 8 , wherein the first plurality of features include measurements of communications sent via the social networking service.

12. The system of claim 8 , wherein the first plurality of features include transaction attributes.

13. The system of claim 8 , wherein the supervised machine learning algorithm is a binary logistic regression model.

14. The system of claim 8 , wherein the determining includes comparing the engagement score for the first member to a threshold value corresponding to attributes of the first member.

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 sample member usage information for a plurality of members in a social networking service, the sample member usage information comprising a plurality of member profiles and, for each member profile, associated usage information regarding graphical user interface interactions with the social networking service, the sample member usage information further comprising, for each member profile, a label indicating an estimated engagement score for the corresponding member, the estimated engagement score indicating a likelihood that the corresponding member will increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members;

for each of the plurality of members:

extracting a first plurality of features from the sample member usage information for the member;

feeding the first plurality of features and the label corresponding to the member into a supervised machine learning algorithm to train an engagement score model to calculate an engagement score for a particular member indicating a probability that the particular member would increase their interactivity with the social networking service if provided with statistical information about confidential data submitted by other members, the particular member being unable to view the confidential data submitted by other members;

obtaining member usage information corresponding to a first member of a social networking service;

extracting a second plurality of features from the member usage information corresponding to the first member;

inputting the second plurality of features into the engagement model to obtain an engagement score for the first member; and

determining whether or not to provide statistical information to the first member about confidential data submitted by other members based on the engagement score for the first member.

16. The non-transitory machine-readable storage medium of claim 15 , wherein the first plurality of features are identical to the second plurality of features.

17. The non-transitory machine-readable storage medium of claim 15 , wherein the first plurality of features are further extracted from a member profile for the member.

18. The non-transitory machine-readable storage medium of claim 15 , wherein the first plurality of features include measurements of communications sent via the social networking service.

19. The non-transitory machine-readable storage medium of claim 15 , wherein the first plurality of features include transaction attributes.

20. The non-transitory machine-readable storage medium of claim 15 , wherein the supervised machine learning algorithm is a binary logistic regression model.