Systems and methods for automated page category recommendation

1. A computer-implemented method comprising:

receiving, by a computing system, page information associated with a page being created by a user and user information associated with the user creating the page;

calculating, by the computing system, confidence scores for a plurality of categories based on the page information and the user information, wherein

a confidence score for a category is indicative of a likelihood that the category is relevant to the page, and

calculating confidence scores for a plurality of categories comprises:

calculating confidence scores for a first plurality of categories based on a first machine learning model, and

calculating confidence scores for a second plurality of categories based on a second machine learning model;

selecting, by the computing system, one or more categories of the plurality of categories based on the confidence scores; and

presenting, by the computing system, the one or more categories to the user as category recommendations.

2. The computer-implemented method of claim 1 , further comprising filtering the first plurality of categories based on a first confidence score threshold to generate a filtered first set of categories.

3. The computer-implemented method of claim 2 , further comprising ranking categories in the filtered first set of categories and the second plurality of categories based on confidence scores.

4. The computer-implemented method of claim 3 , wherein the ranking categories in the filtered first set of categories and the second plurality of categories comprises ranking each category in the filtered first set of categories ahead of each category in the second plurality of categories.

5. The computer-implemented method of claim 2 , further comprising filtering the second plurality of categories based on a second confidence score threshold to generate a filtered second set of categories.

6. The computer-implemented method of claim 5 , wherein the calculating confidence scores for a plurality of categories further comprises calculating confidence scores for a third set of categories based on a third machine learning model.

7. The computer-implemented method of claim 6 , further comprising ranking categories in the filtered first set of categories, the filtered second set of categories, and the third set of categories based on confidence scores, wherein the ranking comprises:

ranking each category in the filtered first set of categories ahead of each category in the filtered second set of categories, and

ranking each category in the filtered second set of categories ahead of each category in the third set of categories.

8. The computer-implemented method of claim 1 , wherein the selecting one or more categories of the plurality of categories comprises selecting a predetermined number of categories.

9. A system comprising:

at least one processor; and

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

receiving page information associated with a page being created by a user and user information associated with the user creating the page;

calculating confidence scores for a plurality of categories based on the page information and the user information, wherein

a confidence score for a category is indicative of a likelihood that the category is relevant to the page, and

calculating confidence scores for a plurality of categories comprises:

calculating confidence scores for a first plurality of categories based on a first machine learning model, and

calculating confidence scores for a second plurality of categories based on a second machine learning model;

selecting one or more categories of the plurality of categories based on the confidence scores; and

presenting the one or more categories to the user as category recommendations.

10. The system of claim 9 , wherein the method further comprises filtering the first plurality of categories based on a first confidence score threshold to yield a filtered first set of categories.

11. The system of claim 10 , wherein the method further comprises ranking categories in the filtered first set of categories and the second plurality of categories based on confidence score.

12. 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:

receiving page information associated with a page being created by a user and user information associated with the user creating the page;

calculating confidence scores for a plurality of categories based on the page information and the user information, wherein

a confidence score for a category is indicative of a likelihood that the category is relevant to the page, and

calculating confidence scores for a plurality of categories comprises:

calculating confidence scores for a first plurality of categories based on a first machine learning model, and

calculating confidence scores for a second plurality of categories based on a second machine learning model;

selecting one or more categories of the plurality of categories based on the confidence scores; and

presenting the one or more categories to the user as category recommendations.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the method further comprises filtering the first plurality of categories based on a first confidence score threshold to yield a filtered first set of categories.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprises ranking categories in the filtered first set of categories and the second plurality of categories based on confidence score.