Cognitive automated and interactive personalized fashion designing using cognitive fashion scores and cognitive analysis of fashion trends and data

1. A computer-implemented method for automated fashion designing, comprising:

training, by a computer device, computer models using deep learning based computer vision;

identifying, by the computer device, at least one gap using cognitively determined fashionability scores (F-scores), wherein the at least one gap is identified based on: predicted sales of a designed fashion product, and interaction effects of the predicted sales on existing fashion products in a same subcategory; and within a particular F-Score range of the designed fashion product; and

creating, by the computer device, a new fashion design using the computer models and the at least one identified gap.

2. The method of claim 1 , wherein the training the models comprises training the models to perform image classification and object detection using neural network techniques and a corpus of images of existing fashion designs.

3. The method of claim 2 , wherein the training the models comprises training the models to learn how different components of fashion designs are spatially related to one another.

4. The method of claim 1 , wherein the F-scores are determined using cognitive analysis of publicly available fashion data associated with existing fashion designs.

5. The method of claim 4 , wherein the at least one gap is identified based on price elasticity of fashion products in different F-score groups.

6. The method of claim 5 , wherein the at least one gap is identified based on interaction effects and part partial correlations between all the different F-score groups.

7. The method of claim 1 , wherein the creating the new fashion design comprises:

determining plural components to be included in the new fashion design based on the at least one gap; and

combining the plural components into a single design using the trained models.

8. The method of claim 1 , further comprising:

presenting the new fashion design to a user via a user interface;

receiving user input from the user via the user interface; and

revising, by the computer device, the new fashion design using the computer models and based on the user input.

9. The method of claim 8 , wherein the user input comprises a selection of at least one component of the new fashion design that the user likes or a selection of at least one component of the new fashion design that the user dislikes.

10. The method of claim 1 , further comprising:

performing the identifying and the creating plural times to create plural new fashion designs;

identifying, by the computer device, a subset of the plural new fashion designs; and

creating, by the computer device, a common new fashion design using the computer models and based on the subset of the plural new fashion designs.

11. A computer program product for automated fashion designing, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

train computer models using deep learning based computer vision;

identify at least one gap using cognitively determined fashionability scores (F-scores), wherein the at least one gap is identified based on: predicted sales of a designed fashion product, and interaction effects of the predicted sales on existing fashion products in a same subcategory; and within a particular F-Score range of the designed fashion product; and

create a new fashion design using the trained computer models and the at least one identified gap.

12. The computer program product of claim 11 , wherein the training the models comprises:

training the models to perform image classification and object detection using neural network techniques and a corpus of images of existing fashion designs; and

training the models to learn how different components of fashion designs are spatially related to one another.

13. The computer program product of claim 11 , wherein:

the F-scores are determined using cognitive analysis of publicly available fashion data associated with existing fashion designs; and

the group of components is determined using: price elasticity of fashion products in different F-score groups; and interaction effects and part partial correlations between products in the different F-score groups.

14. The computer program product of claim 11 , wherein the program instructions cause the computing device to:

receive user input from a user viewing the new fashion design via a user interface;

determine a new group of components based on the group of components and the user input; and

create a revised new fashion design using the trained computer models and based on the user input.

15. The computer program product of claim 14 , wherein the user input comprises a selection of at least one component of the new fashion design that the user likes or a selection of at least one component of the new fashion design that the user dislikes.

16. The computer program product of claim 11 , wherein the program instructions cause the computing device to:

perform the identifying and the creating plural times to create plural new fashion designs;

identify a subset of the plural new fashion designs; and

create a common new fashion design using the computer models and based on the subset of the plural new fashion designs.

17. A system for automated fashion designing, comprising:

a processor, a computer readable memory, and a computer readable storage medium;

program instructions to train computer models using deep learning based computer vision;

program instructions to identify at least one gap using cognitively determined fashionability scores (F-scores), wherein the at least one gap is identified based on: predicted sales of a designed fashion product, and interaction effects of the predicted sales on existing fashion products in a same subcategory; and within a particular F-Score range of the designed fashion product; and

program instructions to create a new fashion design using the trained computer models and the at least one identified gap.

18. The system of claim 17 , wherein the program instructions further comprise program instructions to:

receive user input from a user viewing the new fashion design via a user interface;

determine a new group of components based on the group of components and the user input; and

create a revised new fashion design using the trained computer models and the new group of components,

wherein the user input comprises a selection of at least one component of the new fashion design that the user likes or a selection of at least one component of the new fashion design that the user dislikes.

19. The system of claim 17 , wherein the program instructions further comprise program instructions to:

perform the identifying and the creating plural times to create plural new fashion designs;

identify a subset of the plural new fashion designs; and

create a common new fashion design using the computer models and based on the subset of the plural new fashion designs.