Systems and methods for machine learning based age bracket determinations

1. A computer-implemented method comprising:

training, by a computing system, a machine learning model to predict an age division for a person based on one or more features to train the machine learning model including a feature that is a percentage of connections of the person having a same age as the person;

applying, by the computing system, the machine learning model to predict an age division for a user;

determining, by the computing system, an age bracket within the age division including a largest number of connections of the user; and

assigning, by the computing system, the determined age bracket to the user.

2. The computer-implemented method of claim 1 , wherein the determining an age bracket within the age division including a largest number of connections of the user is in response to the age division not including a stated age of the user.

3. The computer-implemented method of claim 2 , further comprising:

in response to the age division including the stated age of the user, determining an age bracket within the age division including the stated age.

4. The computer-implemented method of claim 1 , further comprising:

generating a score relating to a preliminary determination of the age division for the user based on the machine learning model.

5. The computer-implemented method of claim 4 , further comprising:

evaluating the score with a threshold associated with a region associated with the user; and

determining the user to be within the age division if the score satisfies the threshold.

6. The computer-implemented method of claim 5 , wherein the threshold relates to a selected accuracy in determination of an age division for a user associated with the region.

7. The computer-implemented method of claim 1 ,

wherein the training the machine learning model is further based on training data including profile information of persons of a social networking system and labels indicating age divisions for the persons, wherein the profile information of the persons includes profile information of persons in different regions.

8. The computer-implemented method of claim 1 , wherein an age of the person is a stated age.

9. The computer-implemented method of claim 1 , wherein the age division and a second age division are based on a dividing age and each of the age division and the second age division include a plurality of age brackets.

10. The computer-implemented method of claim 1 , further comprising:

comparing engagement by users in a plurality of age brackets across a plurality of products.

11. A computing system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the computing system to perform:

training a machine learning model to predict an age division for a person based on one or more features to train the machine learning model including a feature that is a percentage of connections of the person having a same age as the person;

applying the machine learning model to predict an age division for a user;

determining an age bracket within the age division including a largest number of connections of the user; and

assigning the determined age bracket for the user.

12. The system of claim 11 , further comprising:

generating a score relating to a preliminary determination of the age division for the user based on the machine learning model.

13. The system of claim 12 , further comprising:

evaluating the score with a threshold associated with a region associated with the user; and

determining the user to be within the age division if the score satisfies the threshold.

14. The system of claim 13 , wherein the threshold relates to a selected accuracy in determination of an age division for a user associated with the region.

15. The system of claim 11 ,

wherein the training the machine learning model is further based on training data including profile information of persons of a social networking system and labels indicating age divisions for the persons, wherein the profile information of the persons includes profile information of persons in different regions.

16. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

training a machine learning model to predict an age division for a person based on one or more features to train the machine learning model including a feature that is a percentage of connections of the person having a same age as the person;

applying the machine learning model to predict an age division for a user;

determining an age bracket within the age division including a largest number of connections of the user; and

assigning the determined age bracket for the user.

17. The non-transitory computer-readable storage medium of claim 16 , further comprising:

generating a score relating to a preliminary determination of the age division for the user based on the machine learning model.

18. The non-transitory computer-readable storage medium of claim 17 , further comprising:

evaluating the score with a threshold associated with a region associated with the user; and

determining the user to be within the age division if the score satisfies the threshold.

19. The non-transitory computer-readable storage medium of claim 18 , wherein the threshold relates to a selected accuracy in determination of an age division for a user associated with the region.

20. The non-transitory computer-readable storage medium of claim 16 ,

wherein the training the machine learning model based on training data including profile information of persons of a social networking system and labels indicating age divisions for the persons, wherein the profile information of the persons includes profile information of persons in different regions.