Using artificial intelligence to determine a size fit prediction

1. A method, comprising:

training one or more machine learning models using sizing feedback data that includes a specified size of a specific subject and feedback of the specific subject regarding sizing of a plurality of items, and sizing profile data associated with the plurality of items that includes feedback of other subjects regarding sizing of the plurality of items, wherein a first machine learning model of the one or more machine learning models is a neural network machine learning model that is trained using training data that includes the sizing feedback data and the sizing profile data, wherein the neural network machine learning model includes multiple layers, wherein a final layer of the multiple layers outputs a result associated with a size fit prediction indicating a probability a specific item is predicted to be too large, too small, or fit perfectly on the specific subject, wherein new sizing profile data is received after the first machine learning model is trained and used to update to the first machine learning model;

using a processor to determine a predicted size of the specific subject based on the specific subject's estimated size and feedback on items and to determine a predicted size of a specific item based on feedback received from the other subjects, wherein the predicted size of the specific subject is associated with an estimated actual size of the specific subject despite knowing the specified size of the specific subject used to train the one or more machine learning models;

using the first machine learning model to determine a predicted size fit between the specific item and the specific subject, wherein the predicted size fit indicates a probability that the specific item fits the specific subject according to fit preferences associated with the specific subject;

utilizing the predicted size fit to determine a sizing purchase metric that measures an impact sizing has on the specific subject's decision to purchase the specific item, wherein the sizing purchase metric indicates a probability that the specific subject will purchase the specific item, wherein the probability that the specific subject will purchase the specific item is reduced in response to determining a size mismatch between the fit preferences associated with the specific subject and the predicted size of the specific item; and

ranking the specific item among a plurality of items based in part on the determined sizing purchase metric and the determined size mismatch.

2. The method of claim 1 , wherein using the predicted size of the specific subject and the predicted size of the specific item to determine the predicted size fit includes determining a rank order of the specific item with respect to other items.

3. The method of claim 1 , wherein the one or more machine learning models are further trained using a specified size of the specific item.

4. The method of claim 1 , wherein the one or more machine learning models are further trained using specified sizes of the plurality of items.

5. The method of claim 1 , wherein the one or more machine learning models are further trained using specified sizes of the other subjects.

6. The method of claim 1 , wherein the one or more machine learning models are further trained using fit challenges.

7. The method of claim 6 , wherein the fit challenges include a sleeve length, neck size, or chest size fit challenge.

8. The method of claim 1 , wherein the one or more machine learning models are further trained using fit preferences.

9. The method of claim 8 , wherein the fit preferences include a slim, a regular, and a relaxed fit preference.

10. The method of claim 8 , wherein the fit preferences include a loose or a fitted fit preference.

11. The method of claim 1 , wherein the one or more machine learning models are segmented by item categories.

12. The method of claim 11 , wherein the item categories include top, bottom, and footwear.

13. The method of claim 1 , further comprising:

presenting a user interface element to indicate the predicted size fit.

14. The method of claim 13 , wherein the user interface element displays a probability the specific item is too large or too small for the specific subject.

15. The method of claim 13 , wherein the user interface element is a badge displayed next to a representation of the specific item indicating the specific item is likely too large or too small for the specific subject.

16. The method of claim 1 , wherein the specified size of the specific subject includes a top size, bottom size, height, weight, and one of a chest size or cup size.

17. The method of claim 1 , wherein the specific item has a silhouette category.

18. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

training one or more machine learning models using sizing feedback data that includes a specified size of a specific subject and feedback of the specific subject regarding sizing of a plurality of items, and sizing profile data associated with the plurality of items that includes feedback of other subjects regarding sizing of the plurality of items, wherein a first machine learning model of the one or more machine learning models is a neural network machine learning model that is trained using training data that includes the sizing feedback data and the sizing profile data, wherein the neural network machine learning model includes multiple layers, wherein a final layer of the multiple layers outputs a result associated with a size fit prediction indicating a probability a specific item is predicted to be too large, too small, or fit perfectly on the specific subject, wherein new sizing profile data is received after the first machine learning model is trained and used to update to the first machine learning model;

determining a predicted size of the specific subject based on the specific subject's estimated size and feedback on items and a predicted size of a specific item based on feedback received from the other subjects, wherein the predicted size of the specific subject is associated with an estimated actual size of the specific subject despite knowing the specified size of the specific subject used to train the one or more machine learning models;

using the first machine learning model to determine the predicted size fit between the specific item and the specific subject, wherein the predicted size fit indicates a probability that the specific item fits the specific subject according to fit preferences associated with the specific subject;

utilizing the predicted size fit to determine a sizing purchase metric that measures an impact sizing has on the specific subject's decision to purchase the specific item, wherein the sizing purchase metric indicates a probability that the specific subject will purchase the specific item, wherein the probability that the specific subject will purchase the specific item is reduced in response to determining a size mismatch between the fit preferences associated with the specific subject and the predicted size of the specific item; and

ranking the specific item among a plurality of items based in part on the determined sizing purchase metric and the determined size mismatch.

19. A system, comprising:

a processor; and

a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to:

train one or more machine learning models sizing feedback data that includes using a specified size of a specific subject and feedback of the specific subject regarding sizing of a plurality of items, and sizing profile data associated with the plurality of items that includes feedback of other subjects regarding sizing of the plurality of items, wherein a first machine learning model of the one or more machine learning models is a neural network machine learning model that is trained using training data that includes the sizing feedback data and the sizing profile data, wherein the neural network machine learning model includes multiple layers, wherein a final layer of the multiple layers outputs a result associated with a size fit prediction indicating a probability a specific item is predicted to be too large, too small, or fit perfectly on the specific subject, wherein new sizing profile data is received after the first machine learning model is trained and used to update to the first machine learning model;

determine a predicted size of the specific subject based on the specific subject's estimated size and feedback on items and a predicted size of a specific item based on feedback received from the other subjects, wherein the predicted size of the specific subject is associated with an estimated actual size of the specific subject despite knowing the specified size of the specific subject used to train the one or more machine learning models;

use the first machine learning model to determine the predicted size fit between the specific item and the specific subject, wherein the predicted size fit indicates a probability that the specific item fits the specific subject according to fit preferences associated with the specific subject;

utilize the predicted size fit to determine a sizing purchase metric that measures an impact sizing has on the specific subject's decision to purchase the specific item, wherein the sizing purchase metric indicates a probability that the specific subject will purchase the specific item, wherein the probability that the specific subject will purchase the specific item is reduced in response to determining a size mismatch between the fit preferences associated with the specific subject and the predicted size of the specific item; and

rank the specific item among a plurality of items based on the determined sizing purchase metric and the determined size mismatch.